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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 14426
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of organizational units or physical structures, particularly the word for 'office' or 'bureau'

    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
     kaarangay
    -0.71
     للاسماء
    -0.71
     Signalez
    -0.66
    tagHelperRunner
    -0.65
    ChildIndex
    -0.65
     AssemblyTitle
    -0.62
     ujednoznacz
    -0.62
     elettrico
    -0.60
     ویکی‌پدیای
    -0.60
    endphp
    -0.60
    POSITIVE LOGITS
     Bureau
    3.16
    Bureau
    2.70
     BUREAU
    2.52
     bureau
    2.38
    bureau
    1.77
     bureaus
    1.64
     Bure
    1.55
    UREAU
    1.17
     bureaux
    1.14
     бюро
    0.83
    Activations Density 0.001%

    No Known Activations