© 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. 5-CLT-HP
    7. 96268
    Prev
    Next
    INDEX
    Explanations

    code and news articles

    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
     فريبيس
    -0.70
    лактика
    -0.57
    #+#
    -0.56
    󠁢
    -0.55
    AddTagHelper
    -0.52
     stolet
    -0.48
     Пусть
    -0.48
     founded
    -0.47
    جموع
    -0.46
    InputLabel
    -0.46
    POSITIVE LOGITS
    blockList
    0.62
     kasarigan
    0.58
    Bronnen
    0.56
    出版年
    0.52
    例句
    0.51
    InstrumentedTest
    0.48
    onimo
    0.48
    Jeografia
    0.47
    wetter
    0.47
    ósitos
    0.46
    Activations Density 0.002%

    No Known Activations