© 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. 31807
    Prev
    Next
    INDEX
    Explanations

    mathematical formatting or structures in text

    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
    rrggbb
    -0.54
    uos
    -0.51
    InSection
    -0.50
     phases
    -0.49
     సౌకర్య
    -0.48
     cus
    -0.47
    они
    -0.45
    地下
    -0.45
    fontaine
    -0.45
     McFadden
    -0.45
    POSITIVE LOGITS
    ContentAsync
    0.88
    setVerticalGroup
    0.86
    findpost
    0.84
    SourceChecksum
    0.82
    MessageTagHelper
    0.75
    DotNetBar
    0.75
     StatelessWidget
    0.75
    SBATCH
    0.73
     ComVisible
    0.72
     StatefulWidget
    0.72
    Activations Density 0.007%

    No Known Activations