© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5806
    Prev
    Next
    INDEX
    Explanations

    instances of the word related to "can" indicating ability or possibility

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jutant
    -0.65
    iddhar
    -0.65
     }}"></
    -0.65
    </table>
    -0.60
    defaultProps
    -0.60
    wszy
    -0.59
    hoeddwyd
    -0.58
    utnant
    -0.57
    ikistan
    -0.57
    OOTDTY
    -0.57
    POSITIVE LOGITS
    CAN
    1.82
    Can
    1.72
     Can
    1.66
    can
    1.66
     CAN
    1.52
    cans
    1.20
    kan
    1.11
     Cans
    1.09
    Will
    1.04
     Will
    1.02
    Activations Density 0.179%

    No Known Activations