© 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. 21200
    Prev
    Next
    INDEX
    Explanations

    the presence of opening curly braces in code or structured 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
    (!__
    -0.84
    RepeatedField
    -0.78
    ineno
    -0.74
    rrggbb
    -0.71
    aluz
    -0.71
    AsUp
    -0.71
     rigs
    -0.70
    djangoproject
    -0.70
     mpg
    -0.69
    ưới
    -0.69
    POSITIVE LOGITS
    !("{
    0.84
     Walpole
    0.78
    ]<<"
    0.72
    "){
    0.70
     stö
    0.66
    ")
    0.65
    __*/
    0.65
    +":
    0.65
    +".
    0.65
    SourceChecksum
    0.65
    Activations Density 0.048%

    No Known Activations