© 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. 94906
    Prev
    Next
    INDEX
    Explanations

    sigh

    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
    s
    -0.93
    AxisAlignment
    -0.69
    PerformLayout
    -0.68
    shire
    -0.61
     sounding
    -0.61
    sounding
    -0.59
    ValueStyle
    -0.58
    dür
    -0.57
    irchen
    -0.57
    createServer
    -0.56
    POSITIVE LOGITS
    ècie
    0.51
    æus
    0.50
    .*")]
    0.48
     متعلقه
    0.47
    ffekt
    0.47
     Nuss
    0.46
    editor
    0.46
    fible
    0.46
    WebElementEntity
    0.46
     interrupted
    0.45
    Activations Density 0.933%

    No Known Activations