© 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. 22610
    Prev
    Next
    INDEX
    Explanations

    formatted code structures, specifically class and method definitions

    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
    encodeWith
    -0.63
    󠁴
    -0.58
    pytest
    -0.57
     contextLoads
    -0.57
     trade
    -0.56
    createServer
    -0.55
    enlace
    -0.55
    =$((
    -0.53
     Herce
    -0.53
    MessageState
    -0.51
    POSITIVE LOGITS
    ViewFeatures
    0.72
     gabbana
    0.66
     propOrder
    0.62
     insuffisamment
    0.61
    esgue
    0.60
    ":[{
    0.59
    __(/*!
    0.59
     Evangelist
    0.58
    setVerticalGroup
    0.57
     JpaRepository
    0.57
    Activations Density 0.002%

    No Known Activations