© 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. 20-CLT-HP
    4. 75099
    Prev
    Next
    INDEX
    Explanations

    the letter E

    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
     '\\;'
    -0.77
    RegistryLite
    -0.77
    sizeCache
    -0.75
     disambiguazione
    -0.72
    AddTagHelper
    -0.71
    DockStyle
    -0.69
     utafitiHapana
    -0.67
    PDOException
    -0.67
     lenker
    -0.67
    inghouse
    -0.66
    POSITIVE LOGITS
     E
    0.42
    EM
    0.40
    E
    0.39
     base
    0.39
    Em
    0.39
     em
    0.38
    em
    0.38
     eme
    0.38
    ']))
    
    0.38
     Е
    0.38
    Activations Density 0.002%

    No Known Activations