© 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. 5-CLT-HP
    7. 5101
    Prev
    Next
    INDEX
    Explanations

    patterns

    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
     ourselves
    -1.29
     our
    -1.13
    Our
    -0.91
    our
    -0.91
    我们的
    -0.87
     Our
    -0.86
     можем
    -0.85
     우리
    -0.84
    我們的
    -0.81
     ours
    -0.81
    POSITIVE LOGITS
     themselves
    0.65
    "));
    0.63
     ***!
    0.63
    "));
    0.60
     AssemblyTitle
    0.59
    ")]
    0.58
     itself
    0.57
     comunicarse
    0.57
     CreateTagHelper
    0.57
     Référence
    0.56
    Activations Density 0.001%

    No Known Activations