© 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
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15454
    Prev
    Next
    INDEX
    Explanations

    references to specific financial institutions or financial entities

    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
    sizeCache
    -0.87
     Normdatei
    -0.86
    +:+
    -0.80
     onCreateView
    -0.75
     '\\;'
    -0.75
     ExecuteAsync
    -0.74
     disambiguazione
    -0.71
     ModelExpression
    -0.68
    XmlAccessType
    -0.68
     nakalista
    -0.67
    POSITIVE LOGITS
     Deutsche
    2.17
    Deutsche
    1.85
     Goldman
    1.69
     BNP
    1.65
    BNP
    1.42
     Barclays
    1.24
     Citi
    1.13
     JPMorgan
    1.08
    Citi
    1.01
     Deutschen
    0.99
    Activations Density 0.001%

    No Known Activations