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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 45640
    Prev
    Next
    INDEX
    Explanations

    s

    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
    MigrationBuilder
    -0.71
     snippetHide
    -0.70
    حوالہ
    -0.67
    ourites
    -0.63
    Manbalar
    -0.63
    UserScript
    -0.63
     Шта
    -0.61
     Rukh
    -0.60
    Oby
    -0.59
    WebElementEntity
    -0.59
    POSITIVE LOGITS
     of
    0.52
     to
    0.48
    NSURL
    0.46
     Romains
    0.44
     vérit
    0.44
     peines
    0.44
    kloped
    0.43
    Autores
    0.42
     financières
    0.41
     staden
    0.41
    Activations Density 0.043%

    No Known Activations