© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 14624
    Prev
    Next
    INDEX
    Explanations

    medical texts about breath

    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
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.55
     vectorielle
    -0.54
     avancée
    -0.53
     auroit
    -0.52
     engraçadas
    -0.51
    ftagPool
    -0.50
     Roskov
    -0.50
     varandra
    -0.50
     déput
    -0.49
     financière
    -0.49
    POSITIVE LOGITS
     initComponents
    0.66
    ReusableCell
    0.60
    Ing
    0.60
    Trama
    0.60
     recalled
    0.58
    right
    0.56
    EndInit
    0.56
    تقاوى
    0.56
    단
    0.53
    ătate
    0.53
    Activations Density 0.023%

    No Known Activations