© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    something happening

    np_max-act · gemini-2.0-flash
    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
     happens
    -0.62
     ProtoMessage
    -0.60
    kháu
    -0.58
     CreateTagHelper
    -0.57
     happen
    -0.54
     occurs
    -0.54
    pytest
    -0.54
    hilt
    -0.53
    )}_{
    -0.52
    !*\
    -0.52
    POSITIVE LOGITS
     that
    0.93
    that
    0.69
     שוליים
    0.66
    fjspx
    0.62
     loisirs
    0.56
     supérieurs
    0.52
     kwamba
    0.51
     intptr
    0.51
     worthy
    0.48
    +:+
    0.48
    Activations Density 0.001%

    No Known Activations