© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1309
    Prev
    Next
    INDEX
    Explanations

    Code, names, or verses

    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
     تضيفلها
    -0.82
     AssemblyCulture
    -0.75
    ReusableCell
    -0.69
    IndentedString
    -0.66
    KommentareTeilen
    -0.66
    Datuak
    -0.65
     protoimpl
    -0.64
     المعيارى
    -0.62
    UnitTesting
    -0.61
     OFDb
    -0.60
    POSITIVE LOGITS
    περ
    0.43
    Someday
    0.41
     []).
    0.41
    Feeding
    0.40
    ßer
    0.40
     ч
    0.40
     baja
    0.39
     giới
    0.39
    DefaultValue
    0.39
    Pendidikan
    0.39
    Activations Density 0.004%

    No Known Activations