© 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. 10043
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to court judgments and motions

    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
     
    -0.62
     élu
    -0.52
     démission
    -0.51
    OfWeek
    -0.46
    .
    -0.45
     cottura
    -0.44
     accompagné
    -0.44
     réunis
    -0.44
     name
    -0.44
    Picked
    -0.44
    POSITIVE LOGITS
    تقاوى
    0.93
    RenderAtEndOf
    0.90
    MethodManager
    0.89
    AndroidJUnit
    0.89
    contentLoaded
    0.88
     resourceCulture
    0.84
    KURZBESCHREIBUNG
    0.84
     مشين
    0.83
     समीक्षाओं
    0.83
     незавершена
    0.82
    Activations Density 0.015%

    No Known Activations