© 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. 446
    Prev
    Next
    INDEX
    Explanations

    boilerplate text and place names

    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
    Према
    -0.49
    ubei
    -0.48
    LogFactory
    -0.46
    alanta
    -0.45
    rise
    -0.45
     rekomendasi
    -0.45
    Dislikes
    -0.44
    Laure
    -0.44
     NOM
    -0.43
    keeper
    -0.42
    POSITIVE LOGITS
    Hochspringen
    0.71
    InputBorder
    0.69
    ########.
    0.63
    onViewCreated
    0.60
     '\\;'
    0.59
     MenuView
    0.59
    webElementXpaths
    0.57
     wireType
    0.57
    تقاوى
    0.56
    ]='\
    0.56
    Activations Density 0.001%

    No Known Activations