© 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. 8690
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
     Cove
    -1.40
     cove
    -0.96
     Harbor
    -0.73
    cove
    -0.67
     harbor
    -0.57
    Harbor
    -0.55
    consulté
    -0.54
    Parameteri
    -0.52
     GenerationType
    -0.51
    readAs
    -0.50
    POSITIVE LOGITS
     Efq
    0.67
    Sklici
    0.66
     CreateTagHelper
    0.65
    seamnă
    0.62
     Chwiliwch
    0.59
     étoit
    0.55
    gående
    0.54
     leçon
    0.54
    ällor
    0.54
     scuro
    0.54
    Activations Density 0.038%

    No Known Activations