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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 94831
    Prev
    Next
    INDEX
    Explanations

    Rachel

    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
    Rachel
    -1.03
     Rachel
    -1.00
    Scope
    -0.96
    scope
    -0.67
    SCOPE
    -0.66
    rachel
    -0.64
     Scope
    -0.61
    addCriterion
    -0.58
    下载附件
    -0.56
     cello
    -0.55
    POSITIVE LOGITS
    hyrchwyd
    0.67
    awtextra
    0.49
     Partici
    0.49
     Demon
    0.49
    üyük
    0.49
    ernalia
    0.48
    caloosa
    0.48
    ContentAlignment
    0.47
    skosten
    0.47
     Deb
    0.47
    Activations Density 0.044%

    No Known Activations