© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15542
    Prev
    Next
    INDEX
    Explanations

    terms related to bounds, decay rates, and inequalities in mathematical and physical contexts

    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
     незавершена
    -0.69
     Савезне
    -0.67
     Económica
    -0.63
    WriteBarrier
    -0.62
    emptyset
    -0.59
    smt
    -0.58
    multirow
    -0.57
    dafx
    -0.57
     Tampoco
    -0.56
    Conclusie
    -0.56
    POSITIVE LOGITS
    lesssim
    3.00
    ≲
    1.31
    gtr
    0.92
    ≳
    0.77
     calendriers
    0.66
    StoreMessageInfo
    0.62
     iNdEx
    0.57
     convertView
    0.53
     <=",
    0.52
     cucchia
    0.51
    Activations Density 0.001%

    No Known Activations