© 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. 73634
    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
     Lorca
    -0.59
    expandindo
    -0.58
    wang
    -0.56
     étrangère
    -0.54
     eddy
    -0.54
     Wickham
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    queryInterface
    -0.53
     Councils
    -0.52
     occidentale
    -0.52
    POSITIVE LOGITS
    enderror
    0.60
    HtmlAttribute
    0.57
     transfieras
    0.51
    h
    0.46
    __);
    0.44
     Cas
    0.44
    hér
    0.44
     Kat
    0.44
     Henn
    0.43
     
    0.42
    Activations Density 0.000%

    No Known Activations