© 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. 6072
    Prev
    Next
    INDEX
    Explanations

    occurrences of backticks and code snippets within 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
    avajillas
    -0.94
    σθαι
    -0.89
    •••
    -0.87
     Penh
    -0.85
     Paredes
    -0.84
     Ratna
    -0.84
    olith
    -0.82
    HttpContext
    -0.79
     rootReducer
    -0.79
     Hamm
    -0.77
    POSITIVE LOGITS
    :`
    1.52
     `
    1.51
    .`
    1.48
    {`
    1.47
    =`
    1.46
    )`
    1.37
    "`
    1.36
     (`
    1.36
    (`
    1.30
    >`
    1.26
    Activations Density 0.060%

    No Known Activations