© 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. 8841
    Prev
    Next
    INDEX
    Explanations

    oms

    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
    存于互联网档案馆
    -0.65
    oms
    -0.54
    al
    -0.49
    en
    -0.49
    an
    -0.47
    alkan
    -0.47
    SequentialGroup
    -0.47
    iec
    -0.46
    om
    -0.46
    ić
    -0.46
    POSITIVE LOGITS
    LabelTagHelper
    0.70
    MLLoader
    0.62
     Suez
    0.61
    onActivityResult
    0.60
     Braid
    0.59
     Complexes
    0.58
     ratify
    0.58
    birth
    0.56
     Apalagi
    0.56
     Charge
    0.55
    Activations Density 0.054%

    No Known Activations