© 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. 1-RES-MATRYOSHKA-DC
    7. 380
    Prev
    Next
    INDEX
    Explanations

    elements related to matrix indices or labels in mathematical formulas

    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
     Мексичка
    -0.63
    VELOP
    -0.63
    principalTable
    -0.62
    私たちの
    -0.57
     we
    -0.57
     Dostupné
    -0.56
    ORAGE
    -0.55
     فريبيس
    -0.54
     newBuilder
    -0.54
    getDescriptor
    -0.54
    POSITIVE LOGITS
    i
    3.38
     i
    2.45
    ｉ
    1.45
    𝑖
    1.45
    ii
    1.43
    iS
    1.39
    iN
    1.36
    iA
    1.32
    iL
    1.31
    iI
    1.30
    Activations Density 1.679%

    No Known Activations