© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    words and characters belonging to Croatian, Serbian, or Bosnian

    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
    numerusform
    -1.28
    GEBURTSDATUM
    -1.23
     Efq
    -1.02
     nahilalakip
    -0.93
     themſelves
    -0.91
     betweenstory
    -0.89
     myſelf
    -0.88
     Jefus
    -0.86
    AddTagHelper
    -0.86
    CodeAttribute
    -0.83
    POSITIVE LOGITS
      
    0.68
     "
    0.62
     as
    0.57
     last
    0.57
     “
    0.56
     त
    0.55
     to
    0.54
    redux
    0.54
     क
    0.54
     õ
    0.54
    Activations Density 0.441%

    No Known Activations