© 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. 1-CLT-HP
    4. 1013
    Prev
    Next
    INDEX
    Explanations

    iga

    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
    iga
    -1.45
    IGA
    -1.18
    igas
    -0.81
     Recycle
    -0.76
    WriteTagHelper
    -0.75
    Recycle
    -0.69
    IVEREF
    -0.67
    RegressionTest
    -0.60
     Giga
    -0.56
     kasarigan
    -0.54
    POSITIVE LOGITS
    TestingModule
    0.60
    er
    0.59
     sumpay
    0.57
    ably
    0.55
    o
    0.54
    oan
    0.53
    e
    0.52
    ostro
    0.51
    sohn
    0.50
    a
    0.50
    Activations Density 0.011%

    No Known Activations