© 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. 5-CLT-HP
    7. 92149
    Prev
    Next
    INDEX
    Explanations

    coding

    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
     and
    -0.95
    ,
    -0.77
    .
    -0.66
     (
    -0.60
     but
    -0.52
     Even
    -0.47
     [
    -0.46
    ;
    -0.46
    ↵↵
    -0.44
     —
    -0.44
    POSITIVE LOGITS
     Мексичка
    1.19
    <bos>
    0.97
    Autoritní
    0.96
    ViewFeatures
    0.94
    :✨
    0.93
    AndEndTag
    0.93
     незавершена
    0.92
    Personensuche
    0.92
     '\\;'
    0.90
    клопе
    0.88
    Activations Density 0.001%

    No Known Activations