© 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. 4-CLT-HP
    7. 2566
    Prev
    Next
    INDEX
    Explanations

    ready

    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
    NewUrlParser
    -0.77
    RegressionTest
    -0.76
    parsedMessage
    -0.74
    writeFieldEnd
    -0.58
     bezeichneter
    -0.57
    +#+#
    -0.54
    ainville
    -0.54
    SerializedSize
    -0.54
     Normdatei
    -0.52
    tonsoft
    -0.51
    POSITIVE LOGITS
    Carriera
    0.56
     StatefulWidget
    0.49
    warzys
    0.49
     Carey
    0.47
    ResponseWriter
    0.47
    (''
    0.46
    jatel
    0.46
     cref
    0.45
    brand
    0.45
    GetMapping
    0.44
    Activations Density 0.003%

    No Known Activations