© 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. 20-CLT-HP
    7. 74599
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     >=",
    -0.71
    Datuak
    -0.60
     propOrder
    -0.59
    PhysRev
    -0.57
    Diwedd
    -0.57
    CloseOperation
    -0.56
     AssemblyProduct
    -0.56
    principalColumn
    -0.55
    BufferException
    -0.55
     оригіналу
    -0.54
    POSITIVE LOGITS
    cart
    0.47
    CART
    0.46
     estimés
    0.46
     orologio
    0.45
     CART
    0.45
     baratos
    0.45
     drawn
    0.42
    imread
    0.42
    cda
    0.42
    ICD
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.