© 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. 20290
    Prev
    Next
    INDEX
    Explanations

    references to the client object in coding or programming contexts

    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
    Попис
    -0.58
     pousada
    -0.57
    最快更新
    -0.53
    jointe
    -0.51
    isel
    -0.50
    Kew
    -0.50
     Kela
    -0.50
    adata
    -0.50
     Salamanca
    -0.49
    volmente
    -0.49
    POSITIVE LOGITS
     snippetHide
    0.80
     defaultstate
    0.71
     springfox
    0.71
    ExtendWith
    0.70
    Personensuche
    0.67
     فريبيس
    0.66
    extAlignment
    0.65
    +:+
    0.63
    blurRadius
    0.61
    RunWith
    0.60
    Activations Density 0.007%

    No Known Activations