© 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. 736
    Prev
    Next
    INDEX
    Explanations

    code

    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
    SharedCtor
    -0.75
     disambiguazione
    -0.73
     وتسجيلات
    -0.69
     صوتيه
    -0.66
     yyl
    -0.66
    ########.
    -0.60
     camp
    -0.58
    genstein
    -0.58
    SourceChecksum
    -0.56
     AssemblyCulture
    -0.55
    POSITIVE LOGITS
     становника
    0.61
    المشاركات
    0.54
    ParseTree
    0.46
    atmosphère
    0.46
    tagHelper
    0.45
    layout
    0.44
    Handy
    0.44
     POM
    0.44
     muualla
    0.43
     decoração
    0.43
    Activations Density 0.001%

    No Known Activations