© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 78111
    Prev
    Next
    INDEX
    Explanations

    coding/technical language

    np_max-act-logits · 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
    Negative Logits
    ani
    -0.56
     Wikimedijinoj
    -0.52
    LEncoder
    -0.52
    ajs
    -0.52
    ano
    -0.51
    WithIOException
    -0.51
    oo
    -0.50
    ao
    -0.50
     الاطلاع
    -0.48
    er
    -0.47
    POSITIVE LOGITS
    shadowOffset
    0.54
    tours
    0.53
    stem
    0.49
    sang
    0.48
    RenderAtEndOf
    0.48
    PreferredItem
    0.48
     Audiodateien
    0.47
     pymongo
    0.47
     blessé
    0.47
    sandy
    0.47
    Activations Density 0.003%

    No Known Activations