© 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. 24479
    Prev
    Next
    INDEX
    Explanations

    questions indicated by question marks

    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
    XmlAccessorType
    -0.73
    textbf
    -0.50
    CodeAttribute
    -0.49
    TagMode
    -0.48
     Abp
    -0.48
    مصادر
    -0.48
     المعيارى
    -0.47
    таратура
    -0.46
    MathML
    -0.45
    +#+#
    -0.45
    POSITIVE LOGITS
     Chriftian
    0.86
     ویکی‌پدیای
    0.81
     houſe
    0.80
     quæ
    0.78
     insuffisamment
    0.77
    ?".
    0.76
     þat
    0.75
     Efq
    0.75
    queryInterface
    0.74
     RSSSF
    0.73
    Activations Density 0.048%

    No Known Activations