© 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. 23264
    Prev
    Next
    INDEX
    Explanations

    names of notable individuals and their contributions

    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
     فريبيس
    -1.05
     كومونز
    -0.93
    PreferredItem
    -0.92
    migrationBuilder
    -0.88
    sizeCache
    -0.84
     Савезне
    -0.83
    complexContent
    -0.82
     חיצוניים
    -0.82
    ".
    -0.82
    Jeografia
    -0.82
    POSITIVE LOGITS
     previously
    0.48
     earlier
    0.46
     sebelumnya
    0.45
     previous
    0.44
    Sebelumnya
    0.42
    िव
    0.38
     tidligere
    0.38
     *
    0.37
    先前
    0.36
     mạng
    0.36
    Activations Density 0.382%

    No Known Activations