© 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. 13113
    Prev
    Next
    INDEX
    Explanations

    columbia

    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
     runoff
    -1.54
     Runoff
    -1.25
    run
    -0.63
     run
    -0.58
    Run
    -0.56
    ms
    -0.53
     Run
    -0.53
    runner
    -0.51
     runner
    -0.49
     فريبيس
    -0.49
    POSITIVE LOGITS
     تضيفلها
    0.60
    __);
    0.59
    ,:,
    0.58
     ImportError
    0.57
    Blaze
    0.57
     henna
    0.57
    aryen
    0.56
    ZAN
    0.56
    zenio
    0.56
     virulence
    0.56
    Activations Density 0.011%

    No Known Activations