© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 5374
    Prev
    Next
    INDEX
    Explanations

    specific protein motifs involved in immune function and molecular interactions

    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
    исленность
    -0.57
    orari
    -0.57
    msgSender
    -0.54
     mauvaises
    -0.53
     jú
    -0.52
     Gazetteer
    -0.51
    versy
    -0.49
    $^\
    -0.48
    uksessa
    -0.48
    intios
    -0.47
    POSITIVE LOGITS
    StructEnd
    0.75
     Reisedaten
    0.63
    WebControls
    0.61
    irmanship
    0.61
    HomeAsUpEnabled
    0.60
    omock
    0.59
     متعلقه
    0.59
     وتسجيلات
    0.58
    mobileqq
    0.58
     الأصل
    0.57
    Activations Density 1.435%

    No Known Activations