© 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. 4-CLT-HP
    7. 488
    Prev
    Next
    INDEX
    Explanations

    require

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Expense
    -0.63
     courants
    -0.59
     verksamhet
    -0.56
     preuves
    -0.55
     économies
    -0.54
     bénévoles
    -0.54
     Rate
    -0.54
     cérami
    -0.54
     Expansion
    -0.54
     Demand
    -0.53
    POSITIVE LOGITS
     then
    0.62
     now
    0.61
     also
    0.61
     therefore
    0.60
     she
    0.60
     additionally
    0.60
     like
    0.60
     would
    0.59
     however
    0.59
     unless
    0.58
    Activations Density 0.004%

    No Known Activations