© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3428
    Prev
    Next
    INDEX
    Explanations

    the word "prop" in a variety of scientific contexts

    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
    Negative Logits
     发表于
    -0.79
     topsoil
    -0.79
     quail
    -0.75
     Linnaeus
    -0.75
    Parameteri
    -0.74
     Injectable
    -0.73
     Eller
    -0.73
     архивлан
    -0.73
     Humberto
    -0.72
     Terraria
    -0.71
    POSITIVE LOGITS
     prop
    2.58
    prop
    2.56
     Prop
    2.27
    Prop
    2.20
     props
    1.95
    props
    1.81
     PROP
    1.81
     Props
    1.77
    PROP
    1.72
    Props
    1.62
    Activations Density 0.008%

    No Known Activations