© 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. 94791
    Prev
    Next
    INDEX
    Explanations

    GT

    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
    GT
    -0.92
    KommentareTeilen
    -0.81
     AssemblyCulture
    -0.80
    WebElementEntity
    -0.74
    lifier
    -0.73
    Дереккөздер
    -0.73
     nakalista
    -0.73
     AssemblyTitle
    -0.70
    Życiorys
    -0.69
     propOrder
    -0.69
    POSITIVE LOGITS
    y
    0.55
     early
    0.45
     mim
    0.45
     medium
    0.44
     monthly
    0.44
    ed
    0.43
     local
    0.42
     canh
    0.42
    board
    0.40
     partiellement
    0.40
    Activations Density 0.118%

    No Known Activations