© 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. 1-CLT-HP
    7. 11938
    Prev
    Next
    INDEX
    Explanations

    bron

    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
     Bron
    -0.90
    Bron
    -0.89
     bron
    -0.87
    bron
    -0.84
    BRON
    -0.70
     BRON
    -0.65
    ValueStyle
    -0.62
    Slf
    -0.60
    RetentionPolicy
    -0.52
     Fid
    -0.52
    POSITIVE LOGITS
    chitis
    0.66
    chial
    0.56
    yarnpkg
    0.54
    zes
    0.52
    zed
    0.52
    EntityFramework
    0.50
    requireNonNull
    0.50
     šķ
    0.49
    queles
    0.49
    zös
    0.48
    Activations Density 0.087%

    No Known Activations