© 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. 2113
    Prev
    Next
    INDEX
    Explanations

    Web pages and code

    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
     betweenstory
    -0.93
     tartalomajánló
    -0.79
     дописавши
    -0.74
    Datuak
    -0.74
     مشين
    -0.73
    Portail
    -0.71
    __);
    -0.71
     NIOS
    -0.69
    .*")]
    -0.69
     downvoted
    -0.69
    POSITIVE LOGITS
     Co
    0.52
    ↵↵
    0.48
     nuages
    0.48
     
    0.48
     Neuro
    0.48
     Professor
    0.47
     tervez
    0.47
     Director
    0.47
     joindre
    0.47
    вка
    0.47
    Activations Density 0.002%

    No Known Activations