© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78173
    Prev
    Next
    INDEX
    Explanations

    Code snippets and titles

    np_max-act-logits · 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
    Negative Logits
     kasarigan
    -0.75
    Geplaatst
    -0.71
    tôi
    -0.69
    حوالہ
    -0.69
    TintMode
    -0.67
    CppCodeGen
    -0.66
    COUVER
    -0.66
     للاسماء
    -0.66
    UserScript
    -0.65
    uega
    -0.64
    POSITIVE LOGITS
     propOrder
    0.45
    enterOuterAlt
    0.42
    GraphicsUnit
    0.36
    squareup
    0.36
     Pen
    0.36
     ویکی‌پدیای
    0.35
    moduleId
    0.33
    BufferException
    0.32
    \"></
    0.32
    (*
    0.31
    Activations Density 0.007%

    No Known Activations