© 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. 15716
    Prev
    Next
    INDEX
    Explanations

    references to research articles and papers

    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
    期刊论文
    -0.56
     magique
    -0.53
     geslacht
    -0.51
     citoy
    -0.50
     bowiem
    -0.49
    følgelig
    -0.48
     الدولى
    -0.48
    andowski
    -0.45
     nemlig
    -0.45
     mágico
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.83
    MigrationBuilder
    0.69
     الحره
    0.66
     확인함
    0.65
    Попис
    0.60
     SIMBAD
    0.60
     Vikipedi
    0.59
    StoryboardSegue
    0.58
    "]),
    0.57
     arşivlendi
    0.57
    Activations Density 0.116%

    No Known Activations