© 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. 92019
    Prev
    Next
    INDEX
    Explanations

    viral replication

    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
     kasarigan
    -0.90
     مرئيه
    -0.78
     محفوظة
    -0.75
     getItemId
    -0.68
     Replication
    -0.67
     étoient
    -0.66
     nahilalakip
    -0.66
     enfans
    -0.65
     mères
    -0.63
     vérit
    -0.62
    POSITIVE LOGITS
     choice
    0.51
    form
    0.50
    tvguidetime
    0.50
     form
    0.49
     rather
    0.46
    tak
    0.45
     (
    0.45
    invokeLater
    0.44
     strip
    0.43
    perform
    0.43
    Activations Density 1.189%

    No Known Activations