© 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. 45070
    Prev
    Next
    INDEX
    Explanations

    experienced

    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
     experienced
    -2.31
    experienced
    -1.94
    Experienced
    -1.90
     Experienced
    -1.89
     seasoned
    -1.50
     experimentado
    -1.30
     veteran
    -1.27
     ervaren
    -1.15
     respected
    -1.08
     accomplished
    -1.02
    POSITIVE LOGITS
     contextLoads
    0.68
     مرئيه
    0.62
     Horatio
    0.58
     by
    0.57
    риях
    0.57
     Roskov
    0.56
     muualla
    0.56
    ably
    0.55
     onData
    0.55
     Bohemia
    0.55
    Activations Density 0.249%

    No Known Activations