© 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. 6486
    Prev
    Next
    INDEX
    Explanations

    references to the Wasserstein or related distances used in statistical and optimal transport measurements

    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
     far
    -1.35
    far
    -1.16
    Near
    -1.11
     near
    -1.09
    near
    -1.09
    Far
    -1.06
     Near
    -1.03
     Far
    -1.01
     NEAR
    -0.93
     FAR
    -0.92
    POSITIVE LOGITS
     distance
    2.55
    distance
    2.23
     Distance
    2.20
     DISTANCE
    2.00
    Distance
    1.98
     distances
    1.83
    DISTANCE
    1.72
     distancia
    1.62
    distances
    1.45
     Distances
    1.44
    Activations Density 0.035%

    No Known Activations