© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4769
    Prev
    Next
    INDEX
    Explanations

    technical reports

    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
    Portale
    -0.55
     Leagues
    -0.54
    Explicación
    -0.52
    באנגלית
    -0.52
     excuses
    -0.52
    StreetMap
    -0.52
     dur
    -0.51
     Paglinawan
    -0.51
    ProgressHUD
    -0.51
    quième
    -0.50
    POSITIVE LOGITS
    RegressionTest
    0.51
    smithy
    0.48
     karşılaş
    0.45
     mergeFrom
    0.44
    تفصیلات
    0.43
     كومونز
    0.43
     useAppContext
    0.41
    COLLE
    0.41
     مشين
    0.41
    miral
    0.40
    Activations Density 0.000%

    No Known Activations