© 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. 25293
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters typically used in scientific and academic texts

    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
    PreferredItem
    -0.69
     Италијани
    -0.68
    InputTagHelper
    -0.65
     كومونز
    -0.62
     cardíaca
    -0.61
    RenderAtEndOf
    -0.57
    enterOuterAlt
    -0.55
    hasMoreElements
    -0.54
     Portuguesa
    -0.53
    IUrlHelper
    -0.53
    POSITIVE LOGITS
    twimg
    0.71
    nonatomic
    0.56
    Hauptartikel
    0.54
    expandindo
    0.50
    providedIn
    0.50
    RectangleBorder
    0.49
    endphp
    0.49
    openzeppelin
    0.49
    EditorBrowsable
    0.48
    ebenarnya
    0.48
    Activations Density 0.013%

    No Known Activations