© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    example

    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
     Roskov
    -0.68
     doInBackground
    -0.56
    uoco
    -0.56
     muualla
    -0.54
    SPJ
    -0.51
     = 
    -0.51
    әрмәләр
    -0.50
    alige
    -0.50
    CDCl
    -0.49
    󠁮
    -0.49
    POSITIVE LOGITS
    ArrowToggle
    0.55
     basic
    0.55
    Jereo
    0.54
    Xna
    0.52
     significant
    0.51
    Tembelea
    0.49
     NOK
    0.49
     properties
    0.48
    basic
    0.48
     enlistment
    0.48
    Activations Density 0.028%

    No Known Activations