© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 3085
    Prev
    Next
    INDEX
    Explanations

    mentions of physical or digital "cards."

    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
    Negative Logits
    ///</
    -0.56
     Gerrit
    -0.51
    :✨
    -0.51
    Museo
    -0.50
    Étymologie
    -0.50
    ônio
    -0.49
    VersionUID
    -0.49
    OutputType
    -0.48
     plage
    -0.47
     douglas
    -0.47
    POSITIVE LOGITS
     card
    3.48
     Card
    3.25
    Card
    3.16
    card
    3.13
     CARD
    2.98
     cards
    2.86
    CARD
    2.80
     Cards
    2.69
    cards
    2.52
    Cards
    2.48
    Activations Density 0.327%

    No Known Activations