© 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. 0-CLT-HP
    7. 1081
    Prev
    Next
    INDEX
    Explanations

    Washington

    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
    发表于
    -0.60
     Joseph
    -0.54
     Jo
    -0.52
    t
    -0.48
     held
    -0.47
    Joseph
    -0.47
     Cha
    -0.47
    odils
    -0.47
     
    -0.47
     First
    -0.46
    POSITIVE LOGITS
     pitié
    0.91
    WebVitals
    0.88
     amitié
    0.88
     démocr
    0.86
     chré
    0.84
     atteinte
    0.83
     feroit
    0.82
     définiti
    0.82
     enfans
    0.82
     culturelles
    0.82
    Activations Density 0.309%

    No Known Activations