© 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. 4-CLT-HP
    7. 3462
    Prev
    Next
    INDEX
    Explanations

    dialogue

    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
    <bos>
    -0.67
    …”
    -0.53
    }}</
    -0.51
    :^(
    -0.50
    ..."
    -0.49
     explained
    -0.48
    readdir
    -0.48
    ,"
    -0.48
    -"
    -0.46
    …"
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.83
     InputDecoration
    0.76
    writeFieldEnd
    0.66
    InputBorder
    0.66
    makeConstraints
    0.65
    GEBURTSDATUM
    0.63
    MENAFN
    0.60
     Medea
    0.60
    kháu
    0.60
    mybatisplus
    0.59
    Activations Density 0.001%

    No Known Activations