Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73813
    Prev
    Next
    INDEX
    Explanations

    Code, religion

    np_max-act-logits · 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
     Crash
    -0.79
     propOrder
    -0.78
    Accident
    -0.78
     Accident
    -0.77
     Blackout
    -0.77
     Kanu
    -0.76
     Outbreak
    -0.76
     crash
    -0.76
     Opium
    -0.75
    potranspiration
    -0.73
    POSITIVE LOGITS
     qu
    0.65
    
    0.57
     tem
    0.56
    WebVitals
    0.55
     t
    0.42
     strong
    0.42
     vi
    0.39
     Qu
    0.37
     past
    0.37
     kter
    0.37
    Activations Density 0.000%

    No Known Activations