© 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. 4-CLT-HP
    7. 936
    Prev
    Next
    INDEX
    Explanations

    horses

    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
    DeleteBehavior
    -0.78
     PyLong
    -0.65
     Bioaccumulative
    -0.63
     CanadaChoose
    -0.61
    ViewFeatures
    -0.60
    ergies
    -0.60
     متعلقه
    -0.59
    shund
    -0.58
    ViewImports
    -0.56
    endcsname
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.61
    LookAnd
    0.53
     Wickham
    0.49
     समीक्षक
    0.49
    الدراسه
    0.49
    dymyr
    0.45
     pages
    0.43
     exchanges
    0.43
    blox
    0.42
     traditional
    0.42
    Activations Density 0.000%

    No Known Activations