© 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. 95275
    Prev
    Next
    INDEX
    Explanations

    Snakes

    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
     snakes
    -1.21
     snake
    -1.18
     Efq
    -1.18
     itſelf
    -1.16
     myſelf
    -1.16
    脚注の使い方
    -1.16
     purpoſe
    -1.12
     Diſ
    -1.09
     Jefus
    -1.09
    ſelves
    -1.08
    POSITIVE LOGITS
     that
    0.76
    e
    0.75
    ,
    0.75
     or
    0.73
     the
    0.71
    a
    0.71
    .
    0.71
     to
    0.69
     in
    0.67
     and
    0.65
    Activations Density 0.054%

    No Known Activations