© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    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
    MigrationBuilder
    -0.63
    tvguidetime
    -0.57
    ագրություններ
    -0.56
    expandindo
    -0.54
    Искәрмәләр
    -0.54
     defaultstate
    -0.53
    RRect
    -0.47
    AccessorTable
    -0.45
    InstrumentedTest
    -0.45
    .
    -0.44
    POSITIVE LOGITS
     plufieurs
    0.63
     leaſt
    0.59
     coû
    0.59
     ainfi
    0.58
     dépens
    0.58
     mijne
    0.58
     nôtre
    0.57
    yttö
    0.57
    tidaknya
    0.56
    harusnya
    0.56
    Activations Density 0.004%

    No Known Activations