© 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. 12-RES-MATRYOSHKA-DC
    7. 32538
    Prev
    Next
    INDEX
    Explanations

    references to visual elements, specifically insets or images in a document

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    strat
    -0.59
    leroi
    -0.59
     SqlCommand
    -0.58
     Franken
    -0.55
     tuy
    -0.55
     enggak
    -0.55
    itorious
    -0.54
    sieur
    -0.54
    lini
    -0.54
    pportun
    -0.53
    POSITIVE LOGITS
     inset
    1.31
    inset
    1.21
    Inset
    0.94
    Datuak
    0.86
     fotografico
    0.77
     CTS
    0.73
     Insets
    0.72
     Entomol
    0.68
     caged
    0.68
     itſelf
    0.67
    Activations Density 0.000%

    No Known Activations