© 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. 3551
    Prev
    Next
    INDEX
    Explanations

    references to reports or documents related to fortification of food and micronutrient nutrition in specific regions

    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
    IsContent
    -1.27
     AssemblyTitle
    -1.25
     AssemblyCulture
    -1.19
     propOrder
    -1.17
     ModelExpression
    -1.13
    WithIOException
    -1.13
     esternos
    -1.11
    LookAnd
    -1.09
    TestingModule
    -1.05
     ivelany
    -1.04
    POSITIVE LOGITS
     có
    0.32
    ಿದೆ
    0.32
    ilirsiniz
    0.32
    agaimana
    0.31
    <eos>
    0.31
     què
    0.30
    không
    0.27
    ’
    0.27
    午餐
    0.27
     
    0.26
    Activations Density 9.650%

    No Known Activations