© 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. 20-CLT-HP
    7. 73062
    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
     متعلقه
    -1.06
     CreateTagHelper
    -0.90
     contextLoads
    -0.70
    DeleteBehavior
    -0.68
    BagConstraints
    -0.66
     initComponents
    -0.65
    
    -0.64
    Javadoc
    -0.62
    KEYCODE
    -0.59
     onOptions
    -0.59
    POSITIVE LOGITS
     government
    0.69
     Government
    0.63
     reason
    0.61
     language
    0.59
    mor
    0.57
     rhetoric
    0.56
     law
    0.55
     logic
    0.53
     ethics
    0.52
     value
    0.51
    Activations Density 0.000%

    No Known Activations