© 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
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2780
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    exitRule
    -0.68
     resourceCulture
    -0.67
     contextLoads
    -0.65
    Tikang
    -0.63
    UnusedPrivate
    -0.62
    RUnlock
    -0.61
     BorderRadius
    -0.60
    AddTagHelper
    -0.60
     PropTypes
    -0.60
    reportError
    -0.60
    POSITIVE LOGITS
     the
    0.65
     including
    0.54
     pada
    0.50
     Tode
    0.48
     in
    0.46
     during
    0.45
    migrationBuilder
    0.45
     includ
    0.45
     shootings
    0.45
     all
    0.44
    Activations Density 0.009%

    No Known Activations