© 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. 14892
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology, specifically the term "per curiam" in judicial 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
    Chham
    -0.56
    encodeWith
    -0.56
     remb
    -0.53
    Oneof
    -0.53
     purpoſe
    -0.53
     mukana
    -0.52
     Lyndon
    -0.52
     vlasy
    -0.51
     '',
    -0.50
     vst
    -0.50
    POSITIVE LOGITS
     CURIAM
    5.22
     kasarigan
    1.02
    tvguidetime
    0.78
    verwijspagina
    0.77
    Trama
    0.75
     Walkover
    0.69
    来歴
    0.69
    MEMORANDUM
    0.68
    ieteur
    0.65
     ơn
    0.63
    Activations Density 0.000%

    No Known Activations