© 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. 90973
    Prev
    Next
    INDEX
    Explanations

    wing

    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
    évaluateur
    -0.71
     ligiloj
    -0.62
    ContentAsync
    -0.56
    VIAF
    -0.55
     kasarigan
    -0.54
    IntoConstraints
    -0.54
    last
    -0.50
     last
    -0.50
    Last
    -0.47
    thalle
    -0.47
    POSITIVE LOGITS
    igata
    0.62
     initComponents
    0.57
    CppMethod
    0.55
    ineno
    0.52
    MessageState
    0.51
     szóci
    0.50
    editForm
    0.50
    PropertyChanging
    0.50
    rdı
    0.50
    AnchorTagHelper
    0.48
    Activations Density 0.004%

    No Known Activations