© 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. 12738
    Prev
    Next
    INDEX
    Explanations

    contextual descriptions of visual representations and scientific data

    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
    例文帳に追加
    -0.66
    >())
    -0.65
     =>
    -0.54
    expandindo
    -0.51
    aughey
    -0.49
    ="{{$
    -0.49
    ByteString
    -0.48
    λισ
    -0.48
    >(),
    -0.47
    ()))
    -0.47
    POSITIVE LOGITS
     незавершена
    0.70
     Portail
    0.66
    Портал
    0.62
     للمعارف
    0.62
     saurait
    0.59
    bitkan
    0.59
    NameInMap
    0.58
     from
    0.57
     fritas
    0.56
     in
    0.55
    Activations Density 0.096%

    No Known Activations