© 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. 16107
    Prev
    Next
    INDEX
    Explanations

    patents and technology

    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
    Referințe
    -0.57
    BufferException
    -0.57
     complex
    -0.48
    who
    -0.45
    complex
    -0.44
     lộ
    -0.42
    ill
    -0.40
    .
    -0.40
    doi
    -0.40
    point
    -0.40
    POSITIVE LOGITS
     ModelExpression
    0.80
     pleaſure
    0.74
     ſtate
    0.74
     ſta
    0.73
    MessageTagHelper
    0.69
     ftate
    0.69
     purpoſe
    0.69
     Majefty
    0.69
     Monfieur
    0.67
     greateſt
    0.67
    Activations Density 0.007%

    No Known Activations