© 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. 6138
    Prev
    Next
    INDEX
    Explanations

    time

    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
    Often
    -0.71
     Often
    -0.70
     often
    -0.62
    often
    -0.61
     rarely
    -0.54
     Rarely
    -0.54
     rarement
    -0.53
     quelquefois
    -0.52
    UnusedPrivate
    -0.51
     seldom
    -0.50
    POSITIVE LOGITS
    MessageTagHelper
    0.57
    PerformLayout
    0.51
    utnik
    0.51
     Lordships
    0.51
     FetchType
    0.51
    วย
    0.50
    ResumeLayout
    0.50
    Datuak
    0.50
    monary
    0.49
    arbit
    0.49
    Activations Density 0.008%

    No Known Activations