© 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. 1-CLT-HP
    7. 45575
    Prev
    Next
    INDEX
    Explanations

    up

    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
     autorytatywna
    -0.89
     disambiguazione
    -0.85
    
    -0.84
     kaarangay
    -0.82
     ویکی‌پدیای
    -0.80
    setVerticalGroup
    -0.77
     ModelRenderer
    -0.76
    IsContent
    -0.76
    Rhestr
    -0.73
    ьаж
    -0.71
    POSITIVE LOGITS
     of
    0.56
    c
    0.54
    io
    0.52
    ides
    0.50
    non
    0.47
    ↵↵
    0.46
    ide
    0.45
    ia
    0.45
    hed
    0.45
    ias
    0.45
    Activations Density 0.200%

    No Known Activations