© 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. 4922
    Prev
    Next
    INDEX
    Explanations

    directed

    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
    DoubleQuotes
    -0.49
    lüssel
    -0.47
     Killer
    -0.45
     SqlParameter
    -0.44
    FontOfSize
    -0.44
     Kích
    -0.44
     gang
    -0.44
    CodeAttribute
    -0.43
     killer
    -0.43
    ariato
    -0.43
    POSITIVE LOGITS
     ModelExpression
    0.75
    帖最后由
    0.69
    انيف
    0.63
     Réponses
    0.62
    ̍t
    0.61
    XmlAccessType
    0.58
     esboço
    0.57
     ModelRenderer
    0.57
     énergé
    0.56
     démocr
    0.56
    Activations Density 0.007%

    No Known Activations