© 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. 0-RES-MATRYOSHKA-DC
    7. 13618
    Prev
    Next
    INDEX
    Explanations

    references to highlighting or emphasizing a specific element or feature

    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
    AndEndTag
    -1.05
     indisponible
    -0.85
    rrggbb
    -0.80
    matchCondition
    -0.78
     AssemblyCulture
    -0.77
     Réponses
    -0.75
    Espèce
    -0.75
    DockStyle
    -0.75
    GEBURTSDATUM
    -0.75
    LEncoder
    -0.74
    POSITIVE LOGITS
     highlighted
    1.90
    highlighted
    1.59
     underlined
    1.41
     underscored
    0.85
    Highlighted
    0.84
     circled
    0.66
     emphasized
    0.61
     outlined
    0.59
     souligné
    0.58
    lighted
    0.55
    Activations Density 0.003%

    No Known Activations