© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74506
    Prev
    Next
    INDEX
    Explanations

    Firefighters and fire

    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
     invokingState
    -0.61
    estrado
    -0.55
     ngang
    -0.54
     propOrder
    -0.53
     Komunikasi
    -0.53
    ><><
    -0.52
    ilyen
    -0.52
    ungkan
    -0.52
     BoxDecoration
    -0.52
    PerformLayout
    -0.50
    POSITIVE LOGITS
     Secretariat
    0.54
     Neighbourhood
    0.50
    first
    0.50
     firefighters
    0.50
     bomberos
    0.49
    السكان
    0.49
     secretariat
    0.48
    참고
    0.48
     Philly
    0.48
     first
    0.45
    Activations Density 0.001%

    No Known Activations