© 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. 96186
    Prev
    Next
    INDEX
    Explanations

    Code or small business

    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
     usual
    -0.56
     well
    -0.51
     place
    -0.48
     general
    -0.48
     cui
    -0.48
     report
    -0.47
     less
    -0.47
     these
    -0.47
    iz
    -0.47
    Oise
    -0.47
    POSITIVE LOGITS
    Personendaten
    0.79
    endphp
    0.77
    rrggbb
    0.75
    ransition
    0.75
    BufferException
    0.73
     ✭✭
    0.69
    rawDesc
    0.68
    IntoConstraints
    0.68
    oneofs
    0.67
    onViewCreated
    0.66
    Activations Density 0.000%

    No Known Activations