© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    avimas
    -0.44
    ceda
    -0.42
    Very
    -0.40
    fseek
    -0.39
    SO
    -0.38
    $
    -0.38
    sok
    -0.38
     verein
    -0.38
    glGen
    -0.37
    ens
    -0.37
    POSITIVE LOGITS
     للمعارف
    0.84
     nakalista
    0.82
    InputBorder
    0.79
     MediatR
    0.76
    Blurb
    0.73
    queryInterface
    0.71
     ExecuteAsync
    0.70
    PerformLayout
    0.70
     تضيفلها
    0.69
    OrWhiteSpace
    0.69
    Activations Density 0.045%

    No Known Activations