© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    descriptions of items involving pairs of similar objects or components

    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
     couples
    -1.30
    couples
    -1.27
     Couples
    -1.22
    Coup
    -1.09
     Coupling
    -1.09
     coupling
    -1.08
     partners
    -1.04
    Partner
    -1.02
    coupled
    -1.01
     Partner
    -1.00
    POSITIVE LOGITS
     pair
    1.79
    pair
    1.38
     Pair
    1.21
     PAIR
    1.16
     paire
    1.06
    Pair
    1.01
    PAIR
    0.78
     Mar
    0.77
     pairs
    0.77
    margin
    0.73
    Activations Density 0.017%

    No Known Activations