© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    code classes

    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
    NameInMap
    -0.76
    contentLoaded
    -0.73
    TypedDataSet
    -0.63
     Мексичка
    -0.61
    PerformLayout
    -0.61
     समीक्षाएं
    -0.59
     ويكيپيديا
    -0.57
     JpaRepository
    -0.57
     تضيفلها
    -0.56
    ThroughAttribute
    -0.56
    POSITIVE LOGITS
     influence
    0.66
     autorytatywna
    0.60
     voorbeeld
    0.59
     dalamnya
    0.56
    prisingly
    0.56
     significant
    0.53
     overras
    0.53
     enfans
    0.52
    addContainerGap
    0.52
    chiat
    0.52
    Activations Density 0.001%

    No Known Activations