© 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. 0-CLT-HP
    7. 43816
    Prev
    Next
    INDEX
    Explanations

    nursing

    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
     varandra
    -0.85
    帖最后由
    -0.84
    BASEPATH
    -0.71
    combat
    -0.70
     stället
    -0.69
    Notae
    -0.68
    juelas
    -0.68
    orghini
    -0.66
    TagHelper
    -0.66
     مرئيه
    -0.66
    POSITIVE LOGITS
    ting
    0.63
    ics
    0.58
    ized
    0.57
    ially
    0.52
    ness
    0.52
    ses
    0.51
    ures
    0.50
     replacement
    0.50
    sand
    0.49
    ment
    0.49
    Activations Density 0.228%

    No Known Activations