© 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. 4-CLT-HP
    7. 4894
    Prev
    Next
    INDEX
    Explanations

    that

    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
     zaś
    -0.52
     amelyek
    -0.52
    mentable
    -0.47
     Permite
    -0.47
     Vgl
    -0.45
    actylus
    -0.44
    ials
    -0.44
    )]=
    -0.43
    zioso
    -0.43
    Portale
    -0.43
    POSITIVE LOGITS
    出版年
    0.70
     CreateTagHelper
    0.69
    AndEndTag
    0.65
    PageIndex
    0.65
    libft
    0.63
     I
    0.62
     needs
    0.61
    HomeAsUpEnabled
    0.61
     ویکی‌پدی
    0.60
    Handlung
    0.60
    Activations Density 0.002%

    No Known Activations