© 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. 0-CLT-HP
    7. 95412
    Prev
    Next
    INDEX
    Explanations

    occur upon

    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
     occur
    -1.28
     occurs
    -1.24
    occurs
    -1.14
     existence
    -1.09
     upon
    -1.08
     Upon
    -1.05
     UPON
    -1.05
     presence
    -1.04
    presence
    -1.02
    Upon
    -1.02
    POSITIVE LOGITS
    r
    0.55
    ra
    0.54
    RegressionTest
    0.53
    rs
    0.52
     kasarigan
    0.51
     the
    0.50
     so
    0.46
    ks
    0.46
    nt
    0.45
    Carriera
    0.45
    Activations Density 0.049%

    No Known Activations