Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73879
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    np_max-act-logits · 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
    зулта
    -0.75
     resourceCulture
    -0.64
    parsedMessage
    -0.63
    SourceChecksum
    -0.60
    Sucesor
    -0.60
    pewa
    -0.60
    KommentareTeilen
    -0.60
    onces
    -0.57
     MatDialog
    -0.57
    曖昧さ回避
    -0.57
    POSITIVE LOGITS
    Скачать
    0.46
     count
    0.44
     arşivlendi
    0.44
     cy
    0.43
    ietic
    0.43
    RunWith
    0.42
     time
    0.42
     w
    0.41
     Preferencias
    0.41
    査
    0.41
    Activations Density 0.000%

    No Known Activations