© 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. 74960
    Prev
    Next
    INDEX
    Explanations

    technical documentation

    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
    GEBURTSDATUM
    -0.91
    ::_('
    -0.77
    verwijspagina
    -0.77
    Descripció
    -0.75
    RectangleBorder
    -0.73
    ThroughAttribute
    -0.68
    yntaxException
    -0.67
    ніципалі
    -0.66
    bootstrapcdn
    -0.66
    MLLoader
    -0.64
    POSITIVE LOGITS
     more
    0.72
     lebih
    0.50
    opardy
    0.48
    Point
    0.48
     the
    0.47
     even
    0.47
    More
    0.44
    more
    0.43
    Even
    0.43
     due
    0.43
    Activations Density 0.000%

    No Known Activations