© 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. 91671
    Prev
    Next
    INDEX
    Explanations

    parents

    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
     Roskov
    -0.82
    BoxShadow
    -0.62
     समीक्षाओं
    -0.60
     समीक्षक
    -0.57
     архивлан
    -0.56
     للاسماء
    -0.53
    ViewFeatures
    -0.52
    ConstraintMaker
    -0.50
    RequestParam
    -0.50
     doInBackground
    -0.50
    POSITIVE LOGITS
     of
    0.75
     Matti
    0.54
     surrogate
    0.54
     figures
    0.53
    sträger
    0.53
    aterial
    0.52
    MIC
    0.51
    Materiale
    0.51
     projection
    0.50
    Teléfono
    0.50
    Activations Density 0.003%

    No Known Activations