© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5331
    Prev
    Next
    INDEX
    Explanations

    CSS styling-related information

    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
    PositiveButton
    -0.73
    хьтан
    -0.72
    ########.
    -0.71
     للمعارف
    -0.68
    bootstrapcdn
    -0.65
    webElementXpaths
    -0.64
     AssemblyCulture
    -0.62
    URLException
    -0.60
     hObject
    -0.58
     husband
    -0.56
    POSITIVE LOGITS
     margin
    3.44
    margin
    3.31
     Margin
    2.91
    Margin
    2.58
     margins
    2.58
    MARGIN
    2.16
    margins
    1.98
     marginal
    1.80
    marginal
    1.75
    Margins
    1.73
    Activations Density 0.008%

    No Known Activations