© 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. 20-CLT-HP
    7. 74585
    Prev
    Next
    INDEX
    Explanations

    code and descriptions

    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
    KommentareTeilen
    -0.91
     mystery
    -0.81
     Majefty
    -0.78
    rungsseite
    -0.77
     createState
    -0.75
    DeleteBehavior
    -0.74
     استنادى
    -0.73
     الحره
    -0.72
     صوتيه
    -0.71
     uſed
    -0.71
    POSITIVE LOGITS
     ins
    0.56
    my
    0.42
    leg
    0.40
    Ins
    0.38
     Ins
    0.37
     meus
    0.36
     encu
    0.35
     En
    0.35
    omb
    0.35
     Vapor
    0.34
    Activations Density 0.000%

    No Known Activations