© 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. 6265
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    jspx
    -0.60
     Bretaña
    -0.54
     barato
    -0.54
    ContentAsync
    -0.52
     pinulongan
    -0.52
     balans
    -0.50
     frankfurt
    -0.50
     paus
    -0.50
     initComponents
    -0.49
    Assemblée
    -0.48
    POSITIVE LOGITS
    ьаж
    0.62
     propOrder
    0.60
    setVerticalGroup
    0.54
    ctrica
    0.52
    Zeneca
    0.51
     annum
    0.47
     释放
    0.47
     absolutely
    0.46
    haustible
    0.46
    olymers
    0.46
    Activations Density 0.002%

    No Known Activations