© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13506
    Prev
    Next
    INDEX
    Explanations

    cultures/languages

    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
    berdayakan
    -0.73
     présidentielle
    -0.59
     financière
    -0.59
     défauts
    -0.58
    Viitteet
    -0.57
    openzeppelin
    -0.57
     publiques
    -0.57
     Alcott
    -0.56
     públicos
    -0.56
     émotions
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    0.65
    LookAnd
    0.60
    nne
    0.54
    nese
    0.52
     مشين
    0.50
     ProtoMessage
    0.48
    iseerd
    0.48
    PerformLayout
    0.47
     literature
    0.46
    n
    0.45
    Activations Density 0.007%

    No Known Activations