© 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. 24901
    Prev
    Next
    INDEX
    Explanations

    quoted phrases and citations within legal texts

    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
     متعلقه
    -1.00
    ագրություններ
    -0.88
    ValueStyle
    -0.85
    Clik
    -0.81
    aarrggbb
    -0.81
    Vidite
    -0.78
    出版年
    -0.69
    LinkId
    -0.68
    SuccessListener
    -0.66
     InputDecoration
    -0.66
    POSITIVE LOGITS
     solos
    0.46
     cenu
    0.46
    evre
    0.45
    ędzie
    0.45
     chân
    0.43
    abos
    0.43
     acom
    0.43
     Nachweis
    0.42
     maga
    0.42
     igen
    0.41
    Activations Density 0.015%

    No Known Activations