© 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. 4-CLT-HP
    7. 3517
    Prev
    Next
    INDEX
    Explanations

    al

    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
    uno
    -0.48
    ener
    -0.47
     }:
    -0.46
     intégr
    -0.45
     immédi
    -0.44
    bod
    -0.42
     chers
    -0.42
     pescoço
    -0.42
    ig
    -0.41
    Académie
    -0.41
    POSITIVE LOGITS
    TintMode
    0.83
    WebElementEntity
    0.73
     droppings
    0.71
    Попис
    0.70
     nephe
    0.69
     leprosy
    0.67
     архивлан
    0.66
     crocodiles
    0.65
    נטרנט
    0.65
    opsida
    0.65
    Activations Density 0.161%

    No Known Activations