© 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. 38497
    Prev
    Next
    INDEX
    Explanations

    Valves and pumps

    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
     OFDb
    -1.07
    Autoritní
    -1.04
    ंदीखरीदारी
    -1.03
     CreateTagHelper
    -1.01
     مشين
    -1.01
     avoient
    -1.01
     виправивши
    -1.00
    WebVitals
    -0.98
     étoient
    -0.94
    
    -0.93
    POSITIVE LOGITS
    ↵
    0.50
     core
    0.47
     "
    0.46
     
    0.46
     Re
    0.45
     all
    0.44
     set
    0.44
     (
    0.44
     a
    0.44
     the
    0.43
    Activations Density 0.509%

    No Known Activations