© 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. 42322
    Prev
    Next
    INDEX
    Explanations

    March, images, slicing

    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
     Park
    -0.93
     PARK
    -0.79
    Park
    -0.70
     Charles
    -0.65
     filters
    -0.62
     park
    -0.61
     mar
    -0.54
    Charles
    -0.54
     sin
    -0.52
     slice
    -0.52
    POSITIVE LOGITS
    Билгалдахарш
    0.87
    rungsseite
    0.85
     مرئيه
    0.80
     Baillargeon
    0.77
     ujednoznacz
    0.72
     typelib
    0.72
    bkz
    0.66
    AndEndTag
    0.64
    رشف
    0.63
     nôtre
    0.63
    Activations Density 0.081%

    No Known Activations