© 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. 45765
    Prev
    Next
    INDEX
    Explanations

    Angular

    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
    帖最后由
    -0.66
    كتشاف
    -0.62
     NUKAT
    -0.56
    StoryboardSegue
    -0.56
    ///</
    -0.54
    PYX
    -0.53
    lessly
    -0.52
    WireFormatLite
    -0.51
    chée
    -0.50
     typelib
    -0.50
    POSITIVE LOGITS
    i
    0.60
    thold
    0.52
    e
    0.51
    ius
    0.49
    iA
    0.47
    a
    0.47
    iada
    0.46
    FunctionFlags
    0.44
    ią
    0.43
    iato
    0.43
    Activations Density 0.087%

    No Known Activations