© 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. 96178
    Prev
    Next
    INDEX
    Explanations

    Regex

    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
     grig
    -0.45
     resourceCulture
    -0.44
    iedenis
    -0.44
    ForValue
    -0.43
     ausz
    -0.42
     الميل
    -0.42
    zmán
    -0.41
     rag
    -0.40
    //</
    -0.40
     Dyck
    -0.40
    POSITIVE LOGITS
    ps
    0.83
    p
    0.69
    jspx
    0.68
    es
    0.63
    таратура
    0.62
    pl
    0.61
    ftagPool
    0.61
    principalTable
    0.60
    sol
    0.60
     Laplacian
    0.60
    Activations Density 0.006%

    No Known Activations