© 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. 435
    Prev
    Next
    INDEX
    Explanations

    Structured text

    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
    WireFormatLite
    -0.58
    WriteBarrier
    -0.56
    ellant
    -0.54
    TestingModule
    -0.52
    protoimpl
    -0.52
    himu
    -0.51
    JsonKey
    -0.49
     확인함
    -0.49
     triad
    -0.49
    kev
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.77
    archiviato
    0.57
    NOPQRST
    0.53
     محفوظة
    0.52
     Book
    0.52
     the
    0.50
    IGraphics
    0.49
     kerül
    0.49
     AssemblyProduct
    0.48
     book
    0.48
    Activations Density 0.001%

    No Known Activations