© 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. 0-CLT-HP
    7. 92389
    Prev
    Next
    INDEX
    Explanations

    Chelsea

    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
    nsis
    -0.78
     بيها
    -0.75
    yelitis
    -0.74
    DeleteBehavior
    -0.74
    出版年
    -0.73
     nahilalakip
    -0.73
    例句
    -0.71
    userdetails
    -0.71
    ="@+
    -0.69
     Autorizaciones
    -0.68
    POSITIVE LOGITS
     druž
    0.48
    ovka
    0.44
     needing
    0.44
     regras
    0.44
     medži
    0.43
    on
    0.42
     noches
    0.42
     Sociales
    0.41
    apad
    0.41
    Спољашње
    0.40
    Activations Density 1.796%

    No Known Activations