© 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. 427
    Prev
    Next
    INDEX
    Explanations

    Scientific and medical texts

    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
    SourceChecksum
    -0.67
    oredCriteria
    -0.65
     quí
    -0.60
    assertion
    -0.58
    &__
    -0.58
    march
    -0.54
     linkovi
    -0.54
     Tira
    -0.53
    empt
    -0.52
     Tg
    -0.52
    POSITIVE LOGITS
     виправивши
    0.56
    نجليز
    0.49
    principalTable
    0.47
    umented
    0.47
    verwijspagina
    0.46
    حوالہ
    0.46
     démocr
    0.45
    RUnlock
    0.45
    HStack
    0.44
    migrationBuilder
    0.43
    Activations Density 0.025%

    No Known Activations