© 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. 3-RES-MATRYOSHKA-DC
    7. 3050
    Prev
    Next
    INDEX
    Explanations

    the letter "T" representing the transpose of a matrix in mathematical equations

    oai_token-act-pair · gemini-2.0-flash
    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
    uxxxx
    -0.73
    ChildScrollView
    -0.70
     nakalista
    -0.66
     surla
    -0.55
     COVERAGE
    -0.52
     thang
    -0.50
    ########.
    -0.49
    Revenir
    -0.47
     skimage
    -0.46
    salms
    -0.46
    POSITIVE LOGITS
    WriteTagHelper
    0.71
    Dtor
    0.61
    
    0.61
    toyage
    0.60
     AspNetCore
    0.59
     UnityEditor
    0.59
    FormTagHelper
    0.58
    ypeł
    0.56
    że
    0.55
    ciety
    0.54
    Activations Density 0.203%

    No Known Activations