© 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. 20-CLT-HP
    7. 74877
    Prev
    Next
    INDEX
    Explanations

    Code or 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
    Not in Any Lists

    No Comments

    Negative Logits
     relatifs
    -0.59
     adaptés
    -0.58
     últimos
    -0.54
     conmigo
    -0.53
     variés
    -0.50
    past
    -0.50
     fondament
    -0.50
     épocas
    -0.50
    rock
    -0.50
     giusti
    -0.50
    POSITIVE LOGITS
    ⓧ
    0.90
    RenderAtEndOf
    0.85
    MigrationBuilder
    0.77
    httphttps
    0.69
     knex
    0.69
     للاسماء
    0.65
    CloseOperation
    0.63
    SourceChecksum
    0.60
    ::__
    0.58
    évaluateur
    0.58
    Activations Density 0.017%

    No Known Activations