© 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. 14430
    Prev
    Next
    INDEX
    Explanations

    code comments and formatting symbols

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.47
     mut
    -0.39
     or
    -0.38
    typedef
    -0.38
     на
    -0.36
    /
    -0.36
     and
    -0.36
    ItemId
    -0.35
    .
    -0.35
    pera
    -0.34
    POSITIVE LOGITS
     ExecuteAsync
    1.23
     BoxDecoration
    1.19
    +#+
    1.17
    ########.
    1.12
     lenker
    1.10
    parsedMessage
    1.07
    ंदीखरीदारी
    1.06
     ErrIntOverflow
    1.04
    IsMutable
    1.02
     تضيفلها
    1.00
    Activations Density 0.125%

    No Known Activations