© 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. 0-CLT-HP
    7. 1651
    Prev
    Next
    INDEX
    Explanations

    rounded

    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
     rounded
    -0.84
    enol
    -0.77
     reserved
    -0.72
     Reserved
    -0.69
    Reserved
    -0.69
     TextAppearance
    -0.67
    transQ
    -0.67
     RESERVED
    -0.65
    reserved
    -0.65
    OGND
    -0.60
    POSITIVE LOGITS
     So
    0.54
     sementara
    0.52
    nija
    0.50
    tujuan
    0.48
     transfieras
    0.47
     For
    0.47
     kautta
    0.47
     To
    0.46
     Ad
    0.45
    XPATH
    0.45
    Activations Density 0.115%

    No Known Activations