© 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. 90897
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    djangoproject
    -0.41
    atology
    -0.39
    preventDefault
    -0.39
    IntoConstraints
    -0.39
    LayoutConstraint
    -0.38
    CppCodeGen
    -0.38
    msgSender
    -0.37
    himo
    -0.37
     Lieber
    -0.37
    VertexAttrib
    -0.37
    POSITIVE LOGITS
     initComponents
    0.81
    
    0.79
    Personensuche
    0.75
     transférez
    0.65
     Audiodateien
    0.62
     CHAPITRE
    0.59
     defaultstate
    0.57
    WebElementEntity
    0.57
     betweenstory
    0.57
     ◄
    0.56
    Activations Density 0.002%

    No Known Activations