© 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. 0-RES-MATRYOSHKA-DC
    7. 12668
    Prev
    Next
    INDEX
    Explanations

    references to physical storage units or containers

    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
    Box
    -1.06
    BOX
    -0.89
    boxer
    -0.78
     Boxer
    -0.77
    boxing
    -0.68
    boxes
    -0.67
     boxers
    -0.60
    Boxing
    -0.59
    viewBox
    -0.59
     Boxing
    -0.58
    POSITIVE LOGITS
     box
    1.17
     bag
    0.76
    TestingModule
    0.70
    ibatis
    0.68
     TextInputType
    0.67
     هيا
    0.65
     scatola
    0.62
     nourrir
    0.60
     незавершена
    0.60
     saites
    0.58
    Activations Density 0.006%

    No Known Activations