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. 74631
    Prev
    Next
    INDEX
    Explanations

    Scientific contexts

    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
    addContainerGap
    -0.60
     EconPapers
    -0.59
    parsedMessage
    -0.58
    er
    -0.50
    Erstellt
    -0.49
    erus
    -0.46
     relati
    -0.46
    eric
    -0.45
    abestanden
    -0.45
     المعيارى
    -0.45
    POSITIVE LOGITS
    ésultat
    0.73
    calciatore
    0.56
    ViewImports
    0.55
    a
    0.53
    ellees
    0.53
     União
    0.53
    antula
    0.51
    |>
    0.49
    gham
    0.49
     StatefulWidget
    0.48
    Activations Density 0.003%

    No Known Activations