© 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. 45784
    Prev
    Next
    INDEX
    Explanations

    xo

    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
     AssemblyTitle
    -0.57
    outes
    -0.54
    Rujuakan
    -0.53
     Abgerufen
    -0.52
    ArrowToggle
    -0.52
    oute
    -0.51
    ModelAdmin
    -0.51
    Personensuche
    -0.49
    hassee
    -0.49
     Orrell
    -0.48
    POSITIVE LOGITS
     referenties
    0.57
     للاسماء
    0.55
    RenderAtEndOf
    0.52
     costumi
    0.50
    Jem
    0.50
     mapStateToProps
    0.49
     secco
    0.48
    expandindo
    0.48
    BUG
    0.48
     manuelle
    0.47
    Activations Density 0.032%

    No Known Activations