© 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-CLT-HP
    7. 39828
    Prev
    Next
    INDEX
    Explanations

    government/department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Government
    -1.07
    Government
    -0.99
     Governments
    -0.91
     government
    -0.87
     governments
    -0.86
     GOVERNMENT
    -0.80
    government
    -0.72
     Department
    -0.66
    GOVERNMENT
    -0.65
    政府
    -0.63
    POSITIVE LOGITS
     initComponents
    1.04
     of
    0.86
    ьаж
    0.82
    DockStyle
    0.80
     betweenstory
    0.79
    IUrlHelper
    0.79
    Jegyzetek
    0.79
     ProtoMessage
    0.78
    ########.
    0.77
    SharedDtor
    0.77
    Activations Density 1.257%

    No Known Activations