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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 73417
    Prev
    Next
    INDEX
    Explanations

    Imp/Impro related text

    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
    Scénario
    -0.53
    Tikang
    -0.46
    RectangleBorder
    -0.45
    atol
    -0.45
    FXML
    -0.45
    atite
    -0.44
     husk
    -0.44
     للمعارف
    -0.43
    fak
    -0.43
    ropa
    -0.43
    POSITIVE LOGITS
     spéciaux
    0.64
    protoimpl
    0.63
     élas
    0.59
    IndentedString
    0.58
     mères
    0.56
     larmes
    0.54
     fermés
    0.54
     cérami
    0.54
    ărilor
    0.53
    أما
    0.52
    Activations Density 0.003%

    No Known Activations