© 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. 4018
    Prev
    Next
    INDEX
    Explanations

    statements asserting that a certain property or fact holds with high certainty or frequency

    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
     Finally
    -0.76
    Finally
    -0.70
     numberWith
    -0.66
    Tog
    -0.57
    wüns
    -0.57
    s
    -0.57
     наконец
    -0.55
     Tog
    -0.54
     Rasmussen
    -0.53
     Incidentally
    -0.52
    POSITIVE LOGITS
    Moreover
    1.55
     Moreover
    1.55
     moreover
    1.45
    RectangleBorder
    0.86
     Chwiliwch
    0.78
     Misa
    0.77
    Хьажоргаш
    0.76
     HttpResponse
    0.74
    而且
    0.73
    脚注の使い方
    0.72
    Activations Density 0.010%

    No Known Activations