© 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. 4572
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    Hentet
    -0.64
    DockStyle
    -0.61
    ukt
    -0.59
     ostavi
    -0.59
    MigrationBuilder
    -0.58
     ffilmiau
    -0.58
     Italijanski
    -0.57
    SourceChecksum
    -0.57
    setVerticalGroup
    -0.57
    ModelAdmin
    -0.56
    POSITIVE LOGITS
     sóng
    0.42
     cucharadas
    0.40
    CodeDom
    0.40
    ே
    0.40
    riever
    0.40
    session
    0.40
     désolés
    0.40
    لقاء
    0.40
    ResponseWriter
    0.39
    Бахар
    0.39
    Activations Density 0.004%

    No Known Activations