© 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. 5717
    Prev
    Next
    INDEX
    Explanations

    code or software

    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
    hnia
    -0.47
     متحده
    -0.45
    domada
    -0.45
    flora
    -0.43
    rosophila
    -0.43
    migrationBuilder
    -0.42
    apimachinery
    -0.41
    filer
    -0.40
    FromDate
    -0.40
    RULE
    -0.40
    POSITIVE LOGITS
    fjspx
    0.73
    tagext
    0.65
    ArgumentParser
    0.61
     незавершена
    0.60
    ^(@)
    0.60
    ингл
    0.59
     bower
    0.59
    تقاوى
    0.57
    LabelTagHelper
    0.56
     esboço
    0.55
    Activations Density 0.009%

    No Known Activations