© 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. 92420
    Prev
    Next
    INDEX
    Explanations

    theon

    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
    __":
    -1.26
     Мексичка
    -1.15
    __':
    -1.15
     تضيفلها
    -1.13
     pinulongan
    -1.12
    ^(@)
    -1.06
    featureID
    -1.03
    Демографія
    -1.02
    ibatis
    -0.98
     Italijanski
    -0.96
    POSITIVE LOGITS
    ed
    0.77
    en
    0.75
    al
    0.70
    on
    0.66
    o
    0.65
    de
    0.65
    si
    0.63
    li
    0.62
    hi
    0.61
    ime
    0.61
    Activations Density 0.617%

    No Known Activations