© 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. 45602
    Prev
    Next
    INDEX
    Explanations

    most

    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
    setVerticalGroup
    -0.54
    IntoConstraints
    -0.52
    ագրություններ
    -0.52
     "..\..\
    -0.50
    principalTable
    -0.49
     escuchadas
    -0.48
    äng
    -0.48
    upp
    -0.47
    참고
    -0.46
    remot
    -0.46
    POSITIVE LOGITS
    <bos>
    0.67
     of
    0.63
     whoſe
    0.61
     Jefus
    0.60
     whofe
    0.60
     everybody
    0.58
     myſelf
    0.56
    everybody
    0.55
     are
    0.55
     ſta
    0.54
    Activations Density 0.736%

    No Known Activations