© 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. 22-RES-MATRYOSHKA-DC
    7. 1956
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those involving CSS

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Diplomacy
    -0.62
     onCreateView
    -0.61
    MetaObject
    -0.53
     VIAF
    -0.51
     libel
    -0.50
    hänge
    -0.50
     climbers
    -0.50
     Microbiology
    -0.49
     diplomacy
    -0.49
    eleste
    -0.49
    POSITIVE LOGITS
     CSS
    0.98
    CSS
    0.86
    css
    0.82
     css
    0.81
     styles
    0.69
    stylesheet
    0.69
     styling
    0.65
     Sass
    0.65
    Css
    0.65
     Styles
    0.64
    Activations Density 0.364%

    No Known Activations