© 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. 4-CLT-HP
    7. 851
    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
    RegressionTest
    -0.65
     kasarigan
    -0.62
    ########.
    -0.59
    processable
    -0.57
    >');
    -0.52
    /-/
    -0.51
     conséquence
    -0.50
     inconvénients
    -0.48
    >';
    -0.48
     nationaux
    -0.48
    POSITIVE LOGITS
     autorytatywna
    0.72
     himſelf
    0.69
     myſelf
    0.62
     onResponse
    0.59
     themſelves
    0.58
     hObject
    0.55
     itſelf
    0.54
     Yom
    0.52
     decathlon
    0.52
    WebpackPlugin
    0.52
    Activations Density 0.001%

    No Known Activations