© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 38706
    Prev
    Next
    INDEX
    Explanations

    the

    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
     
    -1.01
     the
    -1.00
    ↵
    -0.95
     a
    -0.83
     his
    -0.77
    ↵↵
    -0.74
     (
    -0.73
     in
    -0.69
     that
    -0.68
    -
    -0.65
    POSITIVE LOGITS
    Tembelea
    1.36
    MigrationBuilder
    1.31
    StoryboardSegue
    1.28
     ویکی‌پدیای
    1.27
     itſelf
    1.26
     propOrder
    1.24
    脚注の使い方
    1.20
    WebVitals
    1.17
     مرئيه
    1.17
    ="@+
    1.14
    Activations Density 0.034%

    No Known Activations