© 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. 31330
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to grounds for appeal or defense in court cases

    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
     Walkover
    -0.73
    expandindo
    -0.60
     frage
    -0.58
    BeginContext
    -0.57
     समीक्षक
    -0.56
     Administrativna
    -0.54
    opra
    -0.54
     Italijani
    -0.54
     rând
    -0.53
     Meksiku
    -0.52
    POSITIVE LOGITS
    Reasons
    0.74
     Reasons
    0.71
     reasons
    0.68
    reasons
    0.66
     alternativo
    0.65
    ంగా
    0.63
     причина
    0.61
     Grounds
    0.59
    ModelAdmin
    0.59
     reason
    0.58
    Activations Density 0.073%

    No Known Activations