© 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. 5-CLT-HP
    7. 4519
    Prev
    Next
    INDEX
    Explanations

    domains

    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
     CURIAM
    -0.69
     '\\;'
    -0.65
    awtextra
    -0.62
     createSprite
    -0.60
    ⓧ
    -0.58
     typelib
    -0.57
    SharedDtor
    -0.56
    </tfoot>
    -0.56
     utafitiHapana
    -0.56
    بوابة
    -0.56
    POSITIVE LOGITS
    WebElementEntity
    0.66
    Демографія
    0.47
    lewood
    0.47
     larmes
    0.46
    XmlAccessType
    0.44
    Попис
    0.44
    getActivity
    0.43
    rrggbb
    0.43
    iettivo
    0.43
     nouvel
    0.42
    Activations Density 0.001%

    No Known Activations