© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4003
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings, mediation, and settlement processes

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.64
    MemoryWarning
    -0.57
    ourite
    -0.55
     prioritise
    -0.53
    priority
    -0.49
     aprovechar
    -0.49
     campagnes
    -0.48
    PackageManager
    -0.48
    saraba
    -0.47
     Ditto
    -0.47
    POSITIVE LOGITS
     arbitration
    1.27
     Arbitration
    1.15
     arbitrator
    1.09
     mediation
    1.05
     arbit
    1.02
     arbitrators
    1.02
     Mediation
    0.98
     conciliation
    0.94
    Arbit
    0.92
    arbit
    0.91
    Activations Density 1.202%

    No Known Activations