© 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. 21040
    Prev
    Next
    INDEX
    Explanations

    typesetting and styling attributes in CSS

    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
     يتيمه
    -0.98
     للمعارف
    -0.79
     متعلقه
    -0.71
    UnsafeEnabled
    -0.70
    prefixer
    -0.70
    RenderAtEndOf
    -0.66
     فريبيس
    -0.64
     BoxDecoration
    -0.61
     Wikimedijinoj
    -0.60
    مصادر
    -0.60
    POSITIVE LOGITS
    scalatest
    0.65
    psilon
    0.55
    pygame
    0.54
    apimachinery
    0.52
     ExecuteAsync
    0.50
    setHas
    0.50
     Ney
    0.49
    yeezy
    0.48
     pacientes
    0.48
    jMenuItem
    0.47
    Activations Density 0.002%

    No Known Activations