© 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. 6-RES-MATRYOSHKA-DC
    7. 257
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and expressions

    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
     en
    -0.57
     into
    -0.55
     liên
    -0.52
     tepung
    -0.52
    pektor
    -0.52
     can
    -0.51
     versus
    -0.51
    ulauan
    -0.51
    tekend
    -0.50
     Ge
    -0.50
    POSITIVE LOGITS
     Мексичка
    1.03
    MigrationBuilder
    0.98
    webElementXpaths
    0.92
     الحره
    0.90
    SharedCtor
    0.88
    LookAnd
    0.81
    UserScript
    0.79
    ArrowToggle
    0.78
    IUrlHelper
    0.77
    StructEnd
    0.75
    Activations Density 2.282%

    No Known Activations