© 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. 931
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
     Roskov
    -0.98
     חיצוניים
    -0.83
     hObject
    -0.80
    Архівовано
    -0.77
    期刊论文
    -0.77
     Савезне
    -0.76
    LookAnd
    -0.76
     }}$}
    -0.76
     nakalista
    -0.76
     Wikimedijinoj
    -0.75
    POSITIVE LOGITS
     income
    0.47
     exhaustive
    0.41
     extensive
    0.41
     most
    0.40
     fine
    0.40
    ndorf
    0.39
    :
    0.39
     EX
    0.38
     excluded
    0.38
    чком
    0.38
    Activations Density 0.000%

    No Known Activations