© 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. 42489
    Prev
    Next
    INDEX
    Explanations

    script

    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
     script
    -2.16
    script
    -2.08
     Script
    -1.88
    Script
    -1.79
    cript
    -1.69
     scripting
    -1.63
    SCRIPT
    -1.63
     SCRIPT
    -1.59
     scripts
    -1.56
    cripts
    -1.42
    POSITIVE LOGITS
     ComVisible
    0.88
     ModelExpression
    0.79
    IVEREF
    0.75
    tagext
    0.71
     للمعارف
    0.70
    AccessFile
    0.69
    χεία
    0.69
     NSCoder
    0.68
     electrónicos
    0.66
     automatiques
    0.66
    Activations Density 2.239%

    No Known Activations