© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75647
    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
     kasarigan
    -0.77
    MessageTagHelper
    -0.72
    TagHelper
    -0.67
    Diweddarwch
    -0.65
    ConstraintMaker
    -0.65
    GEBURTSDATUM
    -0.63
    脚注の使い方
    -0.60
    Искәрмәләр
    -0.58
    adaptiveStyles
    -0.57
     дописавши
    -0.57
    POSITIVE LOGITS
     location
    0.52
    Location
    0.50
     mac
    0.48
     turn
    0.47
     mak
    0.47
    BeforeMethod
    0.47
     formation
    0.47
     grading
    0.47
     Location
    0.47
     binnen
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.