© 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. 5-CLT-HP
    7. 95235
    Prev
    Next
    INDEX
    Explanations

    historical events

    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
    htbp
    -0.46
    steuer
    -0.41
     siguiente
    -0.41
    scalatest
    -0.41
     thereafter
    -0.41
     k
    -0.40
    styleable
    -0.40
     expédié
    -0.39
     ca
    -0.39
     Thereafter
    -0.38
    POSITIVE LOGITS
    Personendaten
    0.92
    ^(@)
    0.83
     himſelf
    0.81
     intptr
    0.79
     يتيمه
    0.79
     Sarm
    0.78
     itſelf
    0.77
    scriptcase
    0.74
     وتسجيلات
    0.74
    neſs
    0.73
    Activations Density 0.006%

    No Known Activations