© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4321
    Prev
    Next
    INDEX
    Explanations

    lightning

    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
    folium
    -0.50
     fenó
    -0.48
    let
    -0.45
    Гео
    -0.44
    shout
    -0.44
    rev
    -0.44
     ambao
    -0.44
    folia
    -0.43
     civiles
    -0.42
    cher
    -0.42
    POSITIVE LOGITS
     bugs
    0.86
     fast
    0.80
     bug
    0.73
    bugs
    0.70
    Bugs
    0.68
     McQueen
    0.68
     Bugs
    0.65
    BUG
    0.63
     referenties
    0.62
     otomatig
    0.62
    Activations Density 0.001%

    No Known Activations