© 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. 4-CLT-HP
    7. 4428
    Prev
    Next
    INDEX
    Explanations

    comparisons

    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
     nahilalakip
    -0.64
     is
    -0.58
    Демографія
    -0.57
    AdapterFactory
    -0.47
    '
    -0.46
     видит
    -0.43
    s
    -0.41
    PropertyChanging
    -0.41
     or
    -0.41
    vací
    -0.40
    POSITIVE LOGITS
     belong
    0.85
     do
    0.82
     themſelves
    0.77
     purpoſe
    0.76
     participate
    0.75
     itſelf
    0.73
     deſt
    0.72
     himſelf
    0.72
     uſed
    0.71
     comply
    0.71
    Activations Density 0.001%

    No Known Activations