© 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. 74659
    Prev
    Next
    INDEX
    Explanations

    Code characters

    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
     issue
    -0.90
    rungsseite
    -0.85
     issues
    -0.76
     ISSUES
    -0.73
    expandindo
    -0.71
     Issue
    -0.70
     ISSUE
    -0.70
     Issues
    -0.70
    enumi
    -0.68
    issue
    -0.66
    POSITIVE LOGITS
     trou
    0.60
    ECONOM
    0.51
    acie
    0.48
    ksikon
    0.48
    probe
    0.48
    trou
    0.47
    σύ
    0.47
     Trou
    0.46
    zlo
    0.46
    difficulty
    0.46
    Activations Density 0.000%

    No Known Activations