© 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. 18176
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets in the 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
    numerusform
    -0.73
    idex
    -0.67
    :✨
    -0.65
    makeText
    -0.63
    nders
    -0.63
    المشاركات
    -0.60
     Pum
    -0.59
    Hozzáférés
    -0.58
     calendriers
    -0.57
     Hathaway
    -0.57
    POSITIVE LOGITS
    pgp
    0.71
    页面存档备份
    0.71
     OnInit
    0.69
    //
    0.65
    webElement
    0.64
    endphp
    0.60
     SafeMath
    0.60
    Rptr
    0.59
    ypep
    0.59
     Keane
    0.59
    Activations Density 0.043%

    No Known Activations