© 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. 92299
    Prev
    Next
    INDEX
    Explanations

    conversational discourse markers

    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
    Datuak
    -0.73
    +#+#
    -0.72
     '\\;'
    -0.54
    AddTagHelper
    -0.53
    wijl
    -0.52
    tvguidetime
    -0.51
     EconPapers
    -0.50
    vode
    -0.50
    ineno
    -0.49
    Externé
    -0.49
    POSITIVE LOGITS
    parsedMessage
    0.62
     not
    0.61
    原始内容存档于
    0.58
    defaultProps
    0.56
     technically
    0.52
    下载附件
    0.51
     Réponses
    0.51
    %)$
    0.50
    Mutagenicity
    0.49
    ServiceTest
    0.49
    Activations Density 0.001%

    No Known Activations