© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    the word "propagation" and its variations

    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
    awtextra
    -0.85
     pinulongan
    -0.77
     itemView
    -0.75
     disambiguazione
    -0.75
     DeV
    -0.74
     ModelExpression
    -0.73
     meringue
    -0.70
     mẽ
    -0.69
    kuuta
    -0.68
    HasForeignKey
    -0.68
    POSITIVE LOGITS
     propagation
    2.69
     propagate
    2.56
     Propagation
    2.50
     propag
    2.45
     propagated
    2.39
     propagating
    2.36
    propag
    2.28
     Propag
    2.23
    Propagation
    2.17
    propagation
    2.17
    Activations Density 0.010%

    No Known Activations