© 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. 2203
    Prev
    Next
    INDEX
    Explanations

    Uncomfortable conditions

    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
     referenties
    -0.63
     réguli
    -0.62
    saurus
    -0.61
     complètes
    -0.61
     cherchez
    -0.60
     rayures
    -0.59
     démocr
    -0.58
     étrangères
    -0.58
     recevez
    -0.58
     lentement
    -0.57
    POSITIVE LOGITS
     areas
    0.60
    Géographie
    0.56
     conditions
    0.55
     places
    0.52
     things
    0.52
     environments
    0.52
     situations
    0.48
     substances
    0.47
     spaces
    0.47
     items
    0.47
    Activations Density 0.001%

    No Known Activations