© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4510
    Prev
    Next
    INDEX
    Explanations

    references to court decisions favoring a party

    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
    Benefit
    -0.59
     Szent
    -0.58
     Benefit
    -0.56
     ángeles
    -0.54
    weber
    -0.54
     financières
    -0.53
    qrstuvwxyz
    -0.53
     cortas
    -0.52
    inės
    -0.52
    LISTEN
    -0.51
    POSITIVE LOGITS
     favor
    3.50
     favour
    3.14
    favor
    2.78
     Favor
    2.75
     favors
    2.69
     FAVOR
    2.66
    Favor
    2.44
     favours
    2.39
     favoring
    2.38
    fav
    2.36
    Activations Density 0.022%

    No Known Activations