© 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. 15625
    Prev
    Next
    INDEX
    Explanations

    legal terminology and roles within court proceedings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.72
    GEBURTSDATUM
    -0.71
    jsdelivr
    -0.67
    omiast
    -0.64
     ostavi
    -0.62
    Hentet
    -0.62
     intptr
    -0.62
    Osob
    -0.61
    Vorlage
    -0.59
    tvguidetime
    -0.59
    POSITIVE LOGITS
     other
    0.43
    確認ください
    0.43
    其次
    0.43
    Other
    0.42
     Otros
    0.42
     Other
    0.40
    copyWith
    0.40
    encodeWith
    0.38
     co
    0.38
    جستارهای
    0.38
    Activations Density 0.148%

    No Known Activations