© 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. 0-CLT-HP
    7. 1716
    Prev
    Next
    INDEX
    Explanations

    agency

    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
     agency
    -1.62
     agencies
    -1.50
     Agencies
    -1.46
    agency
    -1.40
    Agency
    -1.33
     Agency
    -1.30
    Agencies
    -1.25
     agents
    -1.23
     AGENCY
    -1.20
     Agent
    -1.14
    POSITIVE LOGITS
     CGRectMake
    0.47
    kosh
    0.45
     ricorda
    0.45
     IBA
    0.44
     of
    0.43
    kissen
    0.43
    />";
    0.42
     خبری
    0.41
     radium
    0.41
     
    0.41
    Activations Density 0.192%

    No Known Activations