© 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. 1-RES-MATRYOSHKA-DC
    7. 551
    Prev
    Next
    INDEX
    Explanations

    references to the coupling or interaction strength in scientific models or calculations

    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
     related
    -0.70
    Related
    -0.66
     виправивши
    -0.66
    ؤلاء
    -0.66
    related
    -0.65
    bootstrapcdn
    -0.65
     associated
    -0.62
    associated
    -0.61
     RELATED
    -0.60
    jsdelivr
    -0.59
    POSITIVE LOGITS
     coupling
    3.77
     Coupling
    3.50
    coupling
    3.19
    coupled
    2.94
     couplings
    2.86
     coupled
    2.70
    Cou
    2.50
     Coupled
    2.50
    couple
    2.42
     COU
    2.33
    Activations Density 0.156%

    No Known Activations