© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 3236
    Prev
    Next
    INDEX
    Explanations

    of

    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
     kasarigan
    -0.69
     sepen
    -0.59
     laut
    -0.53
     być
    -0.52
    bosity
    -0.50
     שוליים
    -0.49
     ansch
    -0.48
     jLabel
    -0.47
    erven
    -0.47
     dialami
    -0.47
    POSITIVE LOGITS
     and
    0.75
    contentLoaded
    0.68
     XCTest
    0.59
    who
    0.58
     who
    0.58
    ArrowToggle
    0.57
     using
    0.56
    buttonShape
    0.56
     defining
    0.56
     introducing
    0.56
    Activations Density 0.003%

    No Known Activations