© 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. 0-CLT-HP
    4. 92131
    Prev
    Next
    INDEX
    Explanations

    scientific documents

    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
    zeit
    -2.06
     Zeit
    -1.81
    Zeit
    -1.46
     zeit
    -1.12
     tijd
    -0.96
    zeiten
    -0.92
    tijd
    -0.80
     time
    -0.78
     tiden
    -0.78
     thời
    -0.72
    POSITIVE LOGITS
     pleaſure
    0.65
    WebServlet
    0.64
    bootstrapcdn
    0.63
     favou
    0.62
    buttonBar
    0.60
    glades
    0.58
    الإنجليزية
    0.57
     myſelf
    0.57
    CloseOperation
    0.56
     Ngb
    0.56
    Activations Density 0.143%

    No Known Activations