© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 45522
    Prev
    Next
    INDEX
    Explanations

    organizations

    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
    -2.56
     agency
    -2.38
    Agency
    -2.34
     AGENCY
    -2.25
    agency
    -2.08
     Agencies
    -1.38
     agencia
    -1.38
    agence
    -1.23
     agência
    -1.23
     agencies
    -1.20
    POSITIVE LOGITS
     medlemmer
    0.54
     laikā
    0.52
     flesta
    0.52
     černá
    0.50
     thereupon
    0.49
     themſelves
    0.48
     čierna
    0.47
     väli
    0.47
     appuntamento
    0.47
     näh
    0.47
    Activations Density 0.128%

    No Known Activations