© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11907
    Prev
    Next
    INDEX
    Explanations

    curly braces and their variations in syntax

    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
     Dorn
    -0.79
     ſtand
    -0.71
    Maverick
    -0.70
    Tamb
    -0.69
     newInstance
    -0.69
    ViewFeatures
    -0.67
    Dak
    -0.66
    resizingMask
    -0.65
     uſed
    -0.65
     Maverick
    -0.64
    POSITIVE LOGITS
    ="{
    1.06
    !("{
    0.74
    ('{
    0.72
    ("{
    0.71
    HandlerContext
    0.70
    alité
    0.66
     بيها
    0.63
    écri
    0.62
    rouvez
    0.60
     chaves
    0.59
    Activations Density 0.054%

    No Known Activations