© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38567
    Prev
    Next
    INDEX
    Explanations

    Поль

    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
    βά
    -0.51
    ryn
    -0.49
    ъ
    -0.48
    eren
    -0.47
    ilya
    -0.45
     paper
    -0.45
     Gres
    -0.45
    hein
    -0.44
    שע
    -0.44
    koj
    -0.44
    POSITIVE LOGITS
     Baillargeon
    0.75
    帖最后由
    0.72
    saraba
    0.71
    
    0.70
     AspNetCore
    0.68
    openConnection
    0.68
    RunAsync
    0.66
     considérons
    0.66
    expandindo
    0.65
    
    0.65
    Activations Density 0.227%

    No Known Activations