© 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. 2990
    Prev
    Next
    INDEX
    Explanations

    references to legal settlement agreements or discussions

    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
     дописавши
    -0.78
    oa̍t
    -0.77
     Walkover
    -0.64
    RegistryLite
    -0.60
     Perf
    -0.59
    beek
    -0.59
     Galbraith
    -0.58
    RunAsync
    -0.57
     ordf
    -0.57
    RunWith
    -0.56
    POSITIVE LOGITS
     settle
    3.50
     settlement
    3.47
     Settlement
    3.23
     SETTLE
    3.22
     settled
    3.20
     settling
    3.19
    settle
    3.16
     settlements
    3.08
     settles
    3.08
    settlement
    2.98
    Activations Density 0.019%

    No Known Activations