© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75274
    Prev
    Next
    INDEX
    Explanations

    employment, employees, employers

    np_max-act-logits · 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
     supplier
    -0.75
    employer
    -0.73
    supplier
    -0.71
    __);
    -0.70
    Organisation
    -0.68
     Employer
    -0.68
    instructor
    -0.68
     betweenstory
    -0.67
     nakalista
    -0.67
     distributor
    -0.66
    POSITIVE LOGITS
    InputTagHelper
    0.48
    em
    0.46
    ArgumentParser
    0.46
    MemoryWarning
    0.45
    الإنجليزية
    0.45
    StructEnd
    0.44
     nonatomic
    0.43
     виправивши
    0.43
    size
    0.43
     er
    0.43
    Activations Density 0.002%

    No Known Activations