© 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. 8878
    Prev
    Next
    INDEX
    Explanations

    continuing

    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
    Convention
    -0.51
    存于互联网档案馆
    -0.49
    __*/
    -0.48
     haka
    -0.48
     bulkhead
    -0.47
    Subtype
    -0.47
     vé
    -0.46
     ihop
    -0.46
    pmatrix
    -0.46
    eleste
    -0.46
    POSITIVE LOGITS
     становника
    0.65
     للاسماء
    0.65
    protoimpl
    0.62
     care
    0.60
    UnusedPrivate
    0.57
    참고
    0.56
    idosis
    0.53
    stateProvider
    0.52
    kháu
    0.51
    burn
    0.51
    Activations Density 0.054%

    No Known Activations