Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-RES-MATRYOSHKA-DC
    4. 31489
    Prev
    Next
    INDEX
    Explanations

    the city name "Berlin"

    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
    ukone
    -0.73
     Matthews
    -0.72
     Quixote
    -0.72
    存于互联网档案馆
    -0.71
     bå
    -0.70
     pinulongan
    -0.70
    Sack
    -0.69
    icação
    -0.68
     Carmine
    -0.67
     bä
    -0.66
    POSITIVE LOGITS
     Berlin
    1.55
    Berlin
    1.34
     BERLIN
    1.24
     berlin
    1.21
     Berlín
    1.05
    berlin
    0.99
     Berliner
    0.75
    
    0.73
     Brecht
    0.70
    ętr
    0.65
    Activations Density 0.002%

    No Known Activations