© 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. 4-CLT-HP
    7. 2383
    Prev
    Next
    INDEX
    Explanations

    comparisons or quantities

    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
    luiting
    -0.53
    MessageTagHelper
    -0.52
    seamnă
    -0.48
     efectivamente
    -0.46
     setempat
    -0.45
    onomía
    -0.43
    綜合報導
    -0.43
    jeva
    -0.42
    felizmente
    -0.42
     pobre
    -0.40
    POSITIVE LOGITS
     capable
    0.72
     massive
    0.71
     stupendous
    0.71
     extraordinary
    0.71
     larger
    0.71
     comparable
    0.70
     akin
    0.70
     remarkable
    0.70
     amazing
    0.69
     huge
    0.69
    Activations Density 0.002%

    No Known Activations