© 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. 10651
    Prev
    Next
    INDEX
    Explanations

    punctuations and specific symbols related to code formatting

    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
    #+#
    -0.80
    Vidite
    -0.80
    ########.
    -0.77
    awtextra
    -0.76
    abestanden
    -0.75
    Personensuche
    -0.73
     Chwiliwch
    -0.71
     Италијани
    -0.71
    HasAnnotation
    -0.70
    SharedCtor
    -0.70
    POSITIVE LOGITS
     Elimination
    0.70
    Geographie
    0.64
    lessed
    0.62
    ation
    0.61
     Smiley
    0.60
    claimer
    0.60
     elimination
    0.60
     Mald
    0.60
     Сайт
    0.60
    baya
    0.59
    Activations Density 0.116%

    No Known Activations