© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 3149
    Prev
    Next
    INDEX
    Explanations

    scientific studies

    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
    RenderAtEndOf
    -0.79
    Autoritní
    -0.72
     EconPapers
    -0.69
    windowFixed
    -0.66
     AssemblyCulture
    -0.65
    InputTagHelper
    -0.65
     Diſ
    -0.64
    opsida
    -0.63
     beginnetje
    -0.62
    abestanden
    -0.62
    POSITIVE LOGITS
     kasarigan
    0.45
    ioni
    0.41
    stern
    0.41
    knot
    0.40
    utnik
    0.39
    斷
    0.39
    mph
    0.38
    strconv
    0.38
    cester
    0.38
    断
    0.38
    Activations Density 0.004%

    No Known Activations