© 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. 14898
    Prev
    Next
    INDEX
    Explanations

    regular expression patterns and structures within code

    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
     myſelf
    -0.85
     Jefus
    -0.84
     Shakspeare
    -0.83
     becauſe
    -0.79
    ագրություններ
    -0.79
     GoogleFonts
    -0.79
     houſe
    -0.78
    FormTagHelper
    -0.77
     Forumite
    -0.77
     pleaſure
    -0.77
    POSITIVE LOGITS
     Tr
    0.48
     (
    0.47
    гули
    0.47
     sk
    0.46
     k
    0.45
     på
    0.43
     lø
    0.43
    culata
    0.43
     Sch
    0.42
     Pa
    0.41
    Activations Density 0.004%

    No Known Activations