© 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. 3151
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    出版年
    -0.61
     Sexuality
    -0.57
     Krim
    -0.56
     sessionFactory
    -0.51
     kasarigan
    -0.51
    Пло
    -0.51
     createContext
    -0.50
    estand
    -0.50
     frizz
    -0.50
     externi
    -0.49
    POSITIVE LOGITS
    parsedMessage
    0.68
    帖最后由
    0.61
     مرئيه
    0.59
    évaluateur
    0.57
     CURIAM
    0.56
    yorsunuz
    0.49
    owią
    0.48
    flashdata
    0.47
     Réponses
    0.45
    )++;
    0.45
    Activations Density 0.001%

    No Known Activations