© 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. 0-CLT-HP
    7. 42826
    Prev
    Next
    INDEX
    Explanations

    bigger/big

    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
     big
    -2.48
    big
    -2.33
     bigger
    -1.91
    Big
    -1.88
    BIG
    -1.78
     Big
    -1.76
    bigger
    -1.73
     BIG
    -1.72
    biggest
    -1.49
     biggest
    -1.47
    POSITIVE LOGITS
    oted
    0.68
    gie
    0.63
    gies
    0.60
     onBind
    0.52
     sekali
    0.50
    wigs
    0.49
    gee
    0.49
    ged
    0.48
    gy
    0.47
     ole
    0.47
    Activations Density 0.046%

    No Known Activations