© 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. 26956
    Prev
    Next
    INDEX
    Explanations

    the presence of angle brackets

    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
     Panamá
    -0.64
    Suara
    -0.51
    Portály
    -0.50
     bước
    -0.48
     trouvait
    -0.48
     Sucre
    -0.47
    ="$(
    -0.47
     kuva
    -0.45
    PreferredItem
    -0.45
    Fatty
    -0.45
    POSITIVE LOGITS
    +#+#
    0.96
     समीक्षाओं
    0.75
    MessageState
    0.71
     holotype
    0.69
    lossians
    0.68
    namental
    0.66
    Chham
    0.66
    yship
    0.66
    RequestParam
    0.65
     متعلقه
    0.65
    Activations Density 0.004%

    No Known Activations