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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92504
    Prev
    Next
    INDEX
    Explanations

    worshipping

    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
     numberOfRows
    -0.44
    Intérieur
    -0.43
     Schuh
    -0.43
    GraphicsUnit
    -0.43
    ajuato
    -0.40
     verfü
    -0.40
     techo
    -0.38
     sendi
    -0.38
    toupper
    -0.37
    alegal
    -0.37
    POSITIVE LOGITS
    Хьажоргаш
    0.83
     ویکی‌پدی
    0.76
     CreateTagHelper
    0.73
     Roskov
    0.69
    ksikon
    0.69
     ostavi
    0.61
     متعلقه
    0.60
     dioxide
    0.58
    fjspx
    0.58
    期刊论文
    0.57
    Activations Density 0.002%

    No Known Activations