© 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. 491
    Prev
    Next
    INDEX
    Explanations

    Electrical engineering/science

    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
     transformer
    -0.79
    quelize
    -0.71
    poptosis
    -0.69
     Transformer
    -0.67
     سكانية
    -0.66
     aikaa
    -0.61
    transformer
    -0.60
    rdom
    -0.59
    Transformer
    -0.59
     potentiometer
    -0.58
    POSITIVE LOGITS
     EconPapers
    0.46
    Vedi
    0.42
     toe
    0.41
     Y
    0.41
     Cy
    0.40
     Heart
    0.40
     Ror
    0.40
     ferons
    0.40
    Архівовано
    0.40
    Toe
    0.39
    Activations Density 0.087%

    No Known Activations