© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96795
    Prev
    Next
    INDEX
    Explanations

    year 2020

    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
     pleaſure
    -0.57
     hindsight
    -0.57
    leş
    -0.55
     AspNetCore
    -0.55
    醐
    -0.54
    liesslich
    -0.53
    Reak
    -0.51
     look
    -0.51
    ormais
    -0.50
     Ganze
    -0.50
    POSITIVE LOGITS
    TestingModule
    0.75
    featureID
    0.75
    Portale
    0.73
    tagHelperRunner
    0.69
    İstinadlar
    0.65
    AndEndTag
    0.62
    tagext
    0.60
    protoimpl
    0.59
    DropTable
    0.57
     jScrollPane
    0.57
    Activations Density 0.002%

    No Known Activations