© 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. 25015
    Prev
    Next
    INDEX
    Explanations

    numerical values related to statistical measures and characteristics

    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
     ModelExpression
    -0.75
    migrationBuilder
    -0.64
     ThemeData
    -0.64
     незавершена
    -0.63
     المعيارى
    -0.62
    coroutines
    -0.52
    mstyle
    -0.52
    DeleteBehavior
    -0.51
    الإنجليزية
    -0.51
    السكان
    -0.50
    POSITIVE LOGITS
     invece
    0.61
    demás
    0.50
    verns
    0.50
    Pratique
    0.49
     CanadaChoose
    0.47
    noStroke
    0.46
     fausse
    0.45
     kaynağından
    0.45
    アンス
    0.45
     itemList
    0.45
    Activations Density 0.015%

    No Known Activations