© 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. 23980
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or their relevance in mathematical expressions

    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
    SPATH
    -0.67
    bital
    -0.59
     doInBackground
    -0.59
     EconPapers
    -0.56
    iastes
    -0.55
    esgue
    -0.53
    úgó
    -0.52
    はじめに
    -0.51
     tortuga
    -0.51
     Prieto
    -0.50
    POSITIVE LOGITS
    出版年
    0.82
    ngdoc
    0.76
    enumi
    0.73
    .*")]
    0.68
    MessageTagHelper
    0.63
    最快更新
    0.61
    impianto
    0.61
    fores
    0.58
    Javadoc
    0.57
    abstractmethod
    0.57
    Activations Density 0.002%

    No Known Activations