© 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. 4-CLT-HP
    7. 2356
    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
     EconPapers
    -0.54
    redge
    -0.50
     propOrder
    -0.49
    IVersion
    -0.48
     للمعارف
    -0.46
     للاسماء
    -0.45
    TagMode
    -0.44
    niająca
    -0.44
    oraus
    -0.44
     carta
    -0.44
    POSITIVE LOGITS
    醐
    0.71
     veneta
    0.62
    ########.
    0.62
    TypedDataSet
    0.60
     of
    0.59
    Showing
    0.58
    ={`/
    0.57
    úsqueda
    0.56
    ñores
    0.55
    říklad
    0.54
    Activations Density 0.027%

    No Known Activations