© 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. 5-CLT-HP
    7. 91868
    Prev
    Next
    INDEX
    Explanations

    those

    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
     propOrder
    -0.58
     épaules
    -0.58
    :✨
    -0.53
     Computers
    -0.51
    ɵ
    -0.50
     simplicité
    -0.50
     seorang
    -0.50
     ingenieros
    -0.50
     Individuals
    -0.50
     Persons
    -0.50
    POSITIVE LOGITS
     which
    0.69
     that
    0.65
    WillAppear
    0.59
    endpush
    0.59
    ########.
    0.56
     sumpay
    0.55
    WebVitals
    0.55
    which
    0.55
    ^(@)
    0.54
    forName
    0.54
    Activations Density 0.001%

    No Known Activations