© 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. 4-CLT-HP
    7. 445
    Prev
    Next
    INDEX
    Explanations

    colons and references

    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
     accessing
    -0.56
     to
    -0.55
     those
    -0.54
    ModelBuilder
    -0.52
     Every
    -0.52
    every
    -0.50
     every
    -0.49
     geografia
    -0.49
    SpringBootTest
    -0.49
     analysing
    -0.48
    POSITIVE LOGITS
    :✨
    0.87
     face
    0.65
    Билгалдахарш
    0.59
     OFDb
    0.58
     الحره
    0.58
    Искәрмәләр
    0.58
     then
    0.57
     SearchView
    0.55
    ArrowToggle
    0.55
    afficheront
    0.55
    Activations Density 0.001%

    No Known Activations