© 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. 3924
    Prev
    Next
    INDEX
    Explanations

    references to legal parties involved in litigation or legal proceedings

    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
     plates
    -1.12
    PLATE
    -1.12
     Plate
    -1.10
     дописавши
    -1.09
    plates
    -1.07
     plate
    -1.06
     Plates
    -1.06
    plate
    -1.02
     plat
    -1.02
    plantas
    -1.02
    POSITIVE LOGITS
     plaintiff
    1.78
     Plaintiff
    1.06
     plaintiffs
    0.86
    Plaintiff
    0.75
     petitioner
    0.72
     PLAINTIFF
    0.66
     claimant
    0.60
    e
    0.52
    ly
    0.52
    mu
    0.52
    Activations Density 0.021%

    No Known Activations