© 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. 0-RES-MATRYOSHKA-DC
    7. 11229
    Prev
    Next
    INDEX
    Explanations

    references to specific brand or product names, especially related to "EZ" or "EZ" as a key identifier

    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
    elemField
    -0.58
     ruang
    -0.54
     мәкал
    -0.53
    ffilm
    -0.52
     numberWith
    -0.49
    mybatisplus
    -0.49
    ftagPool
    -0.49
     Destinations
    -0.49
     Kno
    -0.49
    ↩
    -0.49
    POSITIVE LOGITS
    ez
    3.70
     ez
    1.93
    EZ
    1.78
    Ez
    1.59
     Ez
    1.37
    eze
    1.13
     EZ
    0.89
    eez
    0.77
    yez
    0.72
    ezy
    0.69
    Activations Density 0.000%

    No Known Activations