© 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. 1-CLT-HP
    7. 15808
    Prev
    Next
    INDEX
    Explanations

    code

    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
    nga
    -1.38
    paq
    -0.96
    oba
    -0.76
    addPreferredGap
    -0.61
     Raff
    -0.60
    ODO
    -0.59
     Hing
    -0.59
    InputBorder
    -0.58
    vations
    -0.57
    iffa
    -0.56
    POSITIVE LOGITS
    theless
    0.55
     ostavi
    0.54
     resourceCulture
    0.52
    riwal
    0.52
    RegistryLite
    0.49
    Botswana
    0.49
     unknownFields
    0.49
    likle
    0.49
     Италијани
    0.48
    contentLoaded
    0.47
    Activations Density 0.015%

    No Known Activations