© 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. 1-CLT-HP
    7. 8748
    Prev
    Next
    INDEX
    Explanations

    ECG and medical tests

    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
     ECG
    -0.69
    eco
    -0.56
    >{@
    -0.53
    IMPORTED
    -0.52
    MediaStore
    -0.51
    MessageTagHelper
    -0.51
    oredCriteria
    -0.51
    bkz
    -0.51
     ModelExpression
    -0.50
     EKG
    -0.49
    POSITIVE LOGITS
    Билгалдахарш
    0.64
    исленность
    0.63
     numberOfRows
    0.62
    KommentareTeilen
    0.60
    \{\\
    0.59
    s
    0.58
     jadx
    0.55
    AndEndTag
    0.54
     Assignee
    0.54
    Jeografia
    0.53
    Activations Density 0.128%

    No Known Activations