© 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. 26889
    Prev
    Next
    INDEX
    Explanations

    references to numerical identifiers, particularly case or docket numbers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.03
    posedge
    -0.96
     للمعارف
    -0.83
    DispatchToProps
    -0.80
    GEBURTSDATUM
    -0.80
    :])
    -0.79
    migrationBuilder
    -0.75
     }}">
    -0.75
     kasarigan
    -0.74
    HomeAsUpEnabled
    -0.72
    POSITIVE LOGITS
     Arhivirano
    0.43
    Географи
    0.39
     Arxivat
    0.39
     others
    0.38
    osis
    0.36
     past
    0.35
     Clim
    0.35
     замо
    0.35
    ่ม
    0.35
    ền
    0.34
    Activations Density 0.005%

    No Known Activations