© 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. 94068
    Prev
    Next
    INDEX
    Explanations

    General topics/news

    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
    world
    -0.93
     plates
    -0.88
    World
    -0.82
    ators
    -0.78
     charges
    -0.70
     contract
    -0.69
    WORLD
    -0.67
     parts
    -0.64
     World
    -0.57
    Contract
    -0.57
    POSITIVE LOGITS
     Efq
    1.19
     Theſe
    1.03
     resourceCulture
    0.89
     uſed
    0.89
     Beſ
    0.88
     himſelf
    0.88
     whoſe
    0.87
     ſeveral
    0.87
     Jefus
    0.86
    TintMode
    0.85
    Activations Density 0.253%

    No Known Activations