© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 90922
    Prev
    Next
    INDEX
    Explanations

    scientific/technical processes

    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
    Negative Logits
    出版年
    -0.75
    Cartney
    -0.45
    бро
    -0.45
    uramente
    -0.45
     activation
    -0.44
    xodo
    -0.43
    nání
    -0.43
    <bos>
    -0.42
     exhaustion
    -0.41
    />";
    -0.41
    POSITIVE LOGITS
    oredCriteria
    0.69
    setVerticalGroup
    0.66
     JScrollPane
    0.60
    SharedDtor
    0.60
    MemoryWarning
    0.60
    pragma
    0.57
     Sinon
    0.56
    FormTagHelper
    0.55
    UnknownFields
    0.55
    ensburg
    0.55
    Activations Density 0.001%

    No Known Activations