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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 14153
    Prev
    Next
    INDEX
    Explanations

    references to elements related to markup language, especially emphasis on the word "markup."

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -0.51
     force
    -0.48
     R
    -0.46
     last
    -0.46
     parroquia
    -0.45
     
    -0.45
    态
    -0.45
     be
    -0.44
     bei
    -0.43
     in
    -0.43
    POSITIVE LOGITS
     markup
    2.13
     Markup
    1.66
    markup
    1.37
    ů
    1.30
    Markup
    1.12
     חיצוניים
    1.02
     Huguen
    0.92
     &___
    0.91
    WindowConstants
    0.91
    expandindo
    0.90
    Activations Density 0.002%

    No Known Activations