© 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. 24963
    Prev
    Next
    INDEX
    Explanations

    references to figures or data visualizations in documents

    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
     ويكيپيديا
    -0.82
     république
    -0.77
    InputBorder
    -0.74
     quæ
    -0.69
     насељу
    -0.69
     charité
    -0.66
     iſt
    -0.66
     AssemblyCulture
    -0.66
     $_"
    -0.64
     purpoſe
    -0.64
    POSITIVE LOGITS
    adaptiveStyles
    0.54
    twimg
    0.50
     Commission
    0.46
     E
    0.46
    IsMutable
    0.46
     e
    0.45
     back
    0.45
     Back
    0.45
    $_['
    0.43
     للمعارف
    0.43
    Activations Density 0.000%

    No Known Activations