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-CLT-HP
    4. 44549
    Prev
    Next
    INDEX
    Explanations

    western

    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
     western
    -1.49
    western
    -1.46
    southern
    -1.45
    eastern
    -1.27
     eastern
    -1.25
     southern
    -1.23
     southwestern
    -1.20
     WESTERN
    -1.17
    northern
    -1.16
     northwestern
    -1.09
    POSITIVE LOGITS
    most
    0.59
     
    0.49
    ized
    0.48
     U
    0.47
    theless
    0.44
     United
    0.42
    ness
    0.42
    ization
    0.41
     clear
    0.40
      
    0.40
    Activations Density 0.048%

    No Known Activations