© 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. 2-RES-MATRYOSHKA-DC
    7. 7645
    Prev
    Next
    INDEX
    Explanations

    the concept of legal amendments and related legal procedural language

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     intptr
    -0.74
     magasiner
    -0.72
     ujednoznacz
    -0.70
    PreferredItem
    -0.69
     propOrder
    -0.67
     مشين
    -0.66
    Παραπομπές
    -0.65
     生命周期
    -0.64
    LEncoder
    -0.63
     ContentValues
    -0.62
    POSITIVE LOGITS
     amended
    2.41
     amend
    2.00
     Amended
    1.87
     amending
    1.78
     amendments
    1.73
    amend
    1.69
     Amend
    1.67
     amendment
    1.65
    Amended
    1.63
     Amendments
    1.61
    Activations Density 0.015%

    No Known Activations