© 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. 96028
    Prev
    Next
    INDEX
    Explanations

    where

    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
    jsdelivr
    -0.68
     مشين
    -0.67
    IntoConstraints
    -0.66
     Vikipedi
    -0.62
    AsUp
    -0.62
    enseignements
    -0.60
     للمعارف
    -0.59
     whilst
    -0.59
    Filmographie
    -0.59
    httphttps
    -0.57
    POSITIVE LOGITS
     the
    0.60
     esterni
    0.49
     people
    0.48
     gyhoeddwyd
    0.44
    ogna
    0.41
    vare
    0.41
     taxpayers
    0.39
     favored
    0.39
    saraba
    0.39
     isother
    0.39
    Activations Density 0.002%

    No Known Activations