© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 849
    Prev
    Next
    INDEX
    Explanations

    which

    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
     سكانية
    -0.76
     通販
    -0.73
    TagMode
    -0.72
     ostavi
    -0.71
    WithIOException
    -0.71
    UnknownFieldSet
    -0.69
     OFDb
    -0.67
     reproducibility
    -0.66
     Мексичка
    -0.65
    webElementXpaths
    -0.64
    POSITIVE LOGITS
    ices
    0.48
    ciens
    0.47
    spi
    0.47
     BitmapFactory
    0.46
     spørs
    0.46
     it
    0.45
     Tip
    0.43
    ers
    0.43
    estation
    0.41
    PositiveButton
    0.41
    Activations Density 0.003%

    No Known Activations