© 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. 38594
    Prev
    Next
    INDEX
    Explanations

    code, technical snippets

    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
    팩
    -0.51
     Kró
    -0.50
    Land
    -0.50
     doméstica
    -0.50
    جستارهای
    -0.49
    반
    -0.49
     aastal
    -0.49
     doméstico
    -0.48
     florales
    -0.48
     Закон
    -0.47
    POSITIVE LOGITS
     beginnetje
    0.68
     ویکی‌پدی
    0.66
     Administrativna
    0.61
    شهاد
    0.61
    govina
    0.60
     endwhile
    0.60
    Referanser
    0.58
     sumpay
    0.58
    AccessorTable
    0.57
    utilisons
    0.56
    Activations Density 2.113%

    No Known Activations