© 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. 0-CLT-HP
    7. 93936
    Prev
    Next
    INDEX
    Explanations

    Naval and nuclear topics

    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
    a
    -0.55
     of
    -0.51
    ,
    -0.51
     en
    -0.50
     klar
    -0.50
    da
    -0.50
     Fink
    -0.49
    ito
    -0.49
    рованного
    -0.48
    z
    -0.47
    POSITIVE LOGITS
    клопе
    0.98
    setVerticalGroup
    0.77
    فایل‌لار
    0.74
     AppColors
    0.74
    anthene
    0.73
    batore
    0.72
     contextLoads
    0.71
    bbene
    0.69
     дописавши
    0.69
    helf
    0.69
    Activations Density 0.143%

    No Known Activations