© 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. 0-CLT-HP
    7. 95404
    Prev
    Next
    INDEX
    Explanations

    legal documents/proceedings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    kie
    -1.01
    dite
    -0.91
     Liberties
    -0.78
    ed
    -0.59
    ne
    -0.57
    nete
    -0.56
    ke
    -0.54
    n
    -0.54
    es
    -0.53
    ing
    -0.53
    POSITIVE LOGITS
    expandindo
    1.20
     initComponents
    1.05
     betweenstory
    0.99
    GEBURTSDATUM
    0.91
    ViewImports
    0.90
    numerusform
    0.88
    -------
    0.87
     дописавши
    0.87
     BoxFit
    0.86
    rungsseite
    0.85
    Activations Density 1.217%

    No Known Activations