© 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. 2601
    Prev
    Next
    INDEX
    Explanations

    gulf bay

    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
    NewRow
    -0.59
    matchCondition
    -0.56
     оригіналу
    -0.50
    PreExecute
    -0.49
    MetaType
    -0.49
     PartialEq
    -0.48
    ANTLR
    -0.48
    GOTREF
    -0.48
    DataMap
    -0.48
    SharedCtor
    -0.48
    POSITIVE LOGITS
     '\\;'
    0.63
     of
    0.62
     protoimpl
    0.61
    findpost
    0.59
    savage
    0.51
     attendre
    0.48
    ftagPool
    0.48
    IUrlHelper
    0.47
    ClientSize
    0.47
     suivie
    0.46
    Activations Density 0.002%

    No Known Activations