© 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. 6272
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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
     '\\;'
    -1.04
     myſelf
    -1.01
     ProtoMessage
    -1.00
    rungsseite
    -0.95
    abestanden
    -0.89
    ReusableCell
    -0.88
     للاسماء
    -0.85
     NSCoder
    -0.85
     resourceCulture
    -0.84
     Мексичка
    -0.83
    POSITIVE LOGITS
     v
    0.52
    :
    0.52
     V
    0.47
     easily
    0.47
     new
    0.45
    ?
    0.44
     even
    0.44
     “
    0.43
     "
    0.42
     S
    0.42
    Activations Density 0.049%

    No Known Activations