© 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. 1131
    Prev
    Next
    INDEX
    Explanations

    interactions

    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
    PhysRev
    -0.52
     שוליים
    -0.51
     الحره
    -0.50
    nair
    -0.48
     חיצוניים
    -0.47
    $_['
    -0.47
    twimg
    -0.46
    %{
    -0.45
    lorette
    -0.44
    webElementGuid
    -0.44
    POSITIVE LOGITS
     Monfieur
    0.79
     purpoſe
    0.67
     quæ
    0.67
     houſe
    0.66
     ModelExpression
    0.64
     myſelf
    0.62
     Sulla
    0.60
     whoſe
    0.60
     ſy
    0.60
     Jefus
    0.60
    Activations Density 0.008%

    No Known Activations