© 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. 2709
    Prev
    Next
    INDEX
    Explanations

    pilot

    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
    sell
    -0.48
     们
    -0.46
     campañas
    -0.46
    úmeros
    -0.46
    ode
    -0.45
    divarius
    -0.45
    timis
    -0.44
    ringe
    -0.44
    ExecuteReader
    -0.43
    STATION
    -0.43
    POSITIVE LOGITS
    GEBURTSDATUM
    0.82
    Autoritní
    0.77
     ModelExpression
    0.70
    StructEnd
    0.67
     препратки
    0.66
    IntoConstraints
    0.66
    новниш
    0.64
    DoubleQuotes
    0.62
     Normdatei
    0.61
     المعيارى
    0.60
    Activations Density 0.001%

    No Known Activations