© 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. 39009
    Prev
    Next
    INDEX
    Explanations

    screws

    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
    الحياه
    -0.64
    <bos>
    -0.60
    oa̍t
    -0.56
    qrstuvwxyz
    -0.55
    бовь
    -0.52
     الرياضيه
    -0.50
    evich
    -0.49
    uterie
    -0.47
    ljiv
    -0.47
    enseignements
    -0.47
    POSITIVE LOGITS
    protoimpl
    0.67
    PyExc
    0.66
     flyknit
    0.59
    libft
    0.57
     Duma
    0.57
     fuels
    0.57
     оригіналу
    0.56
     Reſ
    0.56
     allot
    0.55
     TestBed
    0.55
    Activations Density 0.036%

    No Known Activations