© 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. 3513
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
     незавершена
    -0.62
     the
    -0.62
     all
    -0.56
    ✨:
    -0.52
    ishable
    -0.49
     "..\..\
    -0.45
    )|^{
    -0.45
     that
    -0.44
    IBUS
    -0.44
     those
    -0.44
    POSITIVE LOGITS
    igshid
    0.66
    ValueStyle
    0.62
    IsContent
    0.62
     disambiguazione
    0.61
    Демографія
    0.61
    ContentAsync
    0.60
    sizeCache
    0.60
    oredCriteria
    0.58
    migrationBuilder
    0.58
    :✨
    0.58
    Activations Density 0.003%

    No Known Activations