© 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. 1-CLT-HP
    4. 11985
    Prev
    Next
    INDEX
    Explanations

    Peninsula

    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
     iArr
    -0.56
    arote
    -0.56
    seigneur
    -0.55
     Diputados
    -0.51
    rspec
    -0.51
    astify
    -0.50
     absl
    -0.49
    tonsoft
    -0.49
    ghans
    -0.49
    ائه
    -0.49
    POSITIVE LOGITS
    Население
    0.61
    Démographie
    0.60
    MigrationBuilder
    0.60
    ColumnHeaders
    0.60
    Искәрмәләр
    0.59
    ValueStyle
    0.58
    جغرافيا
    0.57
    mixins
    0.55
    DoubleQuotes
    0.52
    abestanden
    0.52
    Activations Density 0.093%

    No Known Activations