© 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. 7126
    Prev
    Next
    INDEX
    Explanations

    specific stylized numerical and schematic representations, particularly focusing on patterned or decorative uses of symbols and numbers

    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
     rigue
    -0.51
     quarta
    -0.49
     Southwestern
    -0.48
     prochaines
    -0.47
    enumii
    -0.47
    الدراسه
    -0.47
    Humph
    -0.47
    temi
    -0.46
     umě
    -0.46
    ($__
    -0.46
    POSITIVE LOGITS
    ViewFeatures
    1.04
     CreateTagHelper
    0.99
    GEBURTSDATUM
    0.94
     nahilalakip
    0.90
     الحره
    0.86
     AssemblyProduct
    0.84
    NameInMap
    0.83
     Italijani
    0.82
    windowFixed
    0.78
     дописавши
    0.76
    Activations Density 0.624%

    No Known Activations