© 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. 95217
    Prev
    Next
    INDEX
    Explanations

    software/system configuration

    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
    controller
    -0.78
    module
    -0.75
    model
    -0.73
     continúas
    -0.73
    button
    -0.73
    device
    -0.70
    server
    -0.70
    content
    -0.69
    option
    -0.69
    summary
    -0.69
    POSITIVE LOGITS
     myſelf
    0.76
     themſelves
    0.74
     IBRARY
    0.68
     ſeveral
    0.68
     purpoſe
    0.67
     itſelf
    0.66
     Eſ
    0.66
    herself
    0.66
    eſ
    0.65
     Theſe
    0.65
    Activations Density 0.123%

    No Known Activations