© 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. 5-CLT-HP
    7. 3814
    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
     CURIAM
    -0.64
    initComponents
    -0.54
    expandindo
    -0.51
    setupUi
    -0.47
    EnableWeb
    -0.47
    Sklici
    -0.46
     propOrder
    -0.45
     محفوظة
    -0.44
    OrBuilder
    -0.43
     onPostExecute
    -0.43
    POSITIVE LOGITS
     themselves
    0.78
    themselves
    0.66
     themſelves
    0.66
    ſelf
    0.60
     stesso
    0.59
     are
    0.59
    chymal
    0.58
    ſelves
    0.55
     himself
    0.55
    جوايز
    0.55
    Activations Density 0.000%

    No Known Activations