© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 41886
    Prev
    Next
    INDEX
    Explanations

    Orbit

    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
     cherchés
    -0.83
    astify
    -0.77
     ModelExpression
    -0.74
    StoryboardSegue
    -0.70
     disambiguazione
    -0.66
     يتيمه
    -0.65
    出版年
    -0.63
     "..\..\..\
    -0.63
    istible
    -0.62
     Obrador
    -0.62
    POSITIVE LOGITS
     Britann
    0.52
    cloudfront
    0.45
     Caixa
    0.45
    ht
    0.45
     lessor
    0.45
     familiale
    0.44
    主
    0.43
    otre
    0.43
    不及
    0.43
    coa
    0.42
    Activations Density 0.516%

    No Known Activations