© 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. 0-CLT-HP
    4. 38645
    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
    ms
    -0.60
     ms
    -0.57
    ESTAMP
    -0.51
     sons
    -0.50
     benar
    -0.47
    Sampling
    -0.47
     plus
    -0.47
    rency
    -0.46
    extérieur
    -0.45
    Commenting
    -0.44
    POSITIVE LOGITS
    tagHelperRunner
    0.77
     ExecuteAsync
    0.65
     ***!
    0.64
    VolleyError
    0.64
     []:
    0.63
    DoubleQuotes
    0.63
    y
    0.62
     '\\;'
    0.59
     Waray
    0.58
     ویکی‌پدیا
    0.58
    Activations Density 1.674%

    No Known Activations