© 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. 0-CLT-HP
    7. 40018
    Prev
    Next
    INDEX
    Explanations

    restart processes

    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
    weed
    -0.73
    weeds
    -0.72
     الحره
    -0.69
    tapes
    -0.68
     חיצוניים
    -0.68
     }}"></
    -0.66
    msgTypes
    -0.62
     refusé
    -0.60
    raszamy
    -0.60
     tiegħek
    -0.59
    POSITIVE LOGITS
     to
    0.54
     ab
    0.51
     Taktlose
    0.50
     le
    0.48
     '\\;'
    0.46
     in
    0.45
    iseerd
    0.45
     for
    0.45
    같이
    0.44
     if
    0.44
    Activations Density 1.479%

    No Known Activations