© 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. 20-CLT-HP
    7. 72623
    Prev
    Next
    INDEX
    Explanations

    Technical or code snippets

    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
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.51
    marks
    -0.46
    ektiv
    -0.45
    level
    -0.45
     @"/
    -0.44
    AutoScale
    -0.44
     level
    -0.42
    hörigen
    -0.41
    moveToFirst
    -0.41
     emplace
    -0.41
    POSITIVE LOGITS
    UnusedPrivate
    0.63
    BorderFactory
    0.56
     aDecoder
    0.56
    脚注の使い方
    0.56
    APORE
    0.54
    IndentedString
    0.54
    rungsseite
    0.54
    outSlope
    0.53
     Crom
    0.52
    AddHtmlAttribute
    0.52
    Activations Density 0.006%

    No Known Activations