© 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. 0-CLT-HP
    7. 91048
    Prev
    Next
    INDEX
    Explanations

    roles

    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
     AssemblyCulture
    -1.04
     propOrder
    -1.03
     незавершена
    -1.02
     CreateTagHelper
    -1.02
     EconPapers
    -1.01
    出版年
    -0.94
     '\\;'
    -0.91
     initComponents
    -0.91
     صوتيه
    -0.91
    Datuak
    -0.90
    POSITIVE LOGITS
     
    0.50
    ’
    0.45
     Ocean
    0.42
    لیس
    0.42
    '
    0.41
    bori
    0.40
     {
    0.39
    وام
    0.38
    chyma
    0.38
     lý
    0.38
    Activations Density 0.296%

    No Known Activations