Copper catalysts are unique in CO₂ reduction as they allow the formation of C₂₊ products. Depending on the catalysts’ synthesis, product distribution varies significantly: while Cu nanoparticles produce mainly methane and hydrogen, oxide-derived copper leads to ethylene and ethanol. Here, by means of ab initio molecular dynamics on oxygen-depleted models, we identified the ensembles controlling catalytic performance. Upon reconstruction and irrespective of the starting structure, recurrent patterns defined by their coordination and charges appear: metallic Cu⁰, polarized Cu^δ+, and oxidic Cu⁺. These species combine to form 14 ensembles. Among them, 4-(6-)coordinated Cu adatoms and Cu₃^δ+O₃ are responsible for tethering CO₂, while metastable near-surface oxygens in fcc-(111) or (100)-like Cu domains promote C–C bond formation via glyoxylate species, thus triggering selective C₂₊ production at low onset potentials. Our work provides guidelines for modeling complex structural rearrangements under CO₂ reduction conditions and devising new synthetic protocols toward an enhanced catalytic performance.