© 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. 5-CLT-HP
    7. 96616
    Prev
    Next
    INDEX
    Explanations

    small

    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
    脚注の使い方
    -0.71
    omeness
    -0.68
    bitat
    -0.67
    >`;
    -0.65
     vrais
    -0.64
     kasarigan
    -0.63
    исленность
    -0.63
     Мексичка
    -0.63
     meilleures
    -0.60
    nloa
    -0.59
    POSITIVE LOGITS
     children
    0.68
     boys
    0.50
     kids
    0.49
     errors
    0.48
     irregularities
    0.47
     variations
    0.47
     countries
    0.46
     discrepancies
    0.46
     enhancements
    0.46
     differences
    0.45
    Activations Density 0.001%

    No Known Activations