© 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. 95431
    Prev
    Next
    INDEX
    Explanations

    issue

    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
     issue
    -1.65
     Issue
    -1.53
    issue
    -1.44
    Issue
    -1.38
     ISSUE
    -1.30
     issues
    -1.27
    ISSUE
    -1.20
     Issues
    -1.18
    Issues
    -1.05
     ISSUES
    -1.05
    POSITIVE LOGITS
    ValueGeneration
    0.83
    تقاوى
    0.80
    verwijspagina
    0.78
    ⓧ
    0.77
    #+#
    0.71
    bootstrapcdn
    0.71
     Paglinawan
    0.69
    WithIOException
    0.69
     autorytatywna
    0.68
     ExecuteAsync
    0.67
    Activations Density 0.098%

    No Known Activations