© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    as

    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
     ujednoznacz
    -0.64
     portraying
    -0.60
     automating
    -0.58
     trying
    -0.57
     installing
    -0.57
     Wikispecies
    -0.57
    MLLoader
    -0.56
     athletics
    -0.55
    DockStyle
    -0.55
     Familienname
    -0.55
    POSITIVE LOGITS
    ,
    0.72
     $(\
    0.55
     $
    0.54
     ${
    0.54
     (
    0.53
     of
    0.51
     $\
    0.50
     $(
    0.50
    (
    0.47
    $
    0.46
    Activations Density 0.028%

    No Known Activations