© 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. 5-CLT-HP
    7. 264
    Prev
    Next
    INDEX
    Explanations

    Code/gibberish/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
     of
    -0.46
    اط
    -0.44
     inclusive
    -0.43
     die
    -0.42
    View
    -0.39
     ag
    -0.39
     address
    -0.39
     a
    -0.39
     true
    -0.39
     yii
    -0.39
    POSITIVE LOGITS
     للاسماء
    1.12
     المعيارى
    0.87
     <=",
    0.85
    ">//
    0.83
    expandindo
    0.82
     AssemblyTitle
    0.79
     estekak
    0.75
     Италијани
    0.75
    verwijspagina
    0.75
    PreferredItem
    0.73
    Activations Density 0.003%

    No Known Activations