© 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. 5-CLT-HP
    4. 3128
    Prev
    Next
    INDEX
    Explanations

    family

    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
     ويكيپيديا
    -0.54
     الذين
    -0.52
    essoas
    -0.50
    Hozzáférés
    -0.50
     hijas
    -0.48
    swiper
    -0.47
     sogni
    -0.47
    */),
    -0.46
    сылкі
    -0.45
     którzy
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.73
    λιά
    0.57
    LEncoder
    0.56
    enderror
    0.55
    ueux
    0.54
     AssemblyCulture
    0.53
     LoggerFactory
    0.52
    ftagPool
    0.52
     of
    0.51
    ofed
    0.51
    Activations Density 0.000%

    No Known Activations