© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 72072
    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
     itself
    -1.40
    itself
    -1.04
     Itself
    -0.84
     byla
    -0.73
     themselves
    -0.72
     должна
    -0.69
    ంది
    -0.69
     должно
    -0.67
     herself
    -0.66
     powinna
    -0.66
    POSITIVE LOGITS
     himself
    0.94
    himself
    0.75
    scriptcase
    0.59
     посвящен
    0.54
     Himself
    0.51
    HasForeignKey
    0.50
     pinulongan
    0.50
    HtmlAttribute
    0.49
     /\.
    0.49
     lui
    0.49
    Activations Density 0.000%

    No Known Activations