© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15431
    Prev
    Next
    INDEX
    Explanations

    references to Austria and its related entities, especially the country and its capital Vienna

    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
     Welsh
    -0.55
    elem
    -0.55
    entuh
    -0.54
     coll
    -0.52
     Morm
    -0.51
    лько
    -0.51
     Zad
    -0.50
     doInBackground
    -0.50
    dismo
    -0.49
    δες
    -0.48
    POSITIVE LOGITS
     Austria
    2.67
     Austrian
    2.44
    Austria
    2.13
    Aust
    2.11
     aust
    1.89
     austria
    1.86
     Aust
    1.78
     Austro
    1.66
     Österreich
    1.60
     österreich
    1.51
    Activations Density 0.002%

    No Known Activations