© 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. 5-CLT-HP
    7. 96908
    Prev
    Next
    INDEX
    Explanations

    to

    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
     चीज़ों
    -0.54
     Pascual
    -0.52
    extracted
    -0.49
     OFDb
    -0.48
     erupted
    -0.47
    readFileSync
    -0.47
    rshire
    -0.47
     Koss
    -0.46
    resso
    -0.46
    (!__
    -0.46
    POSITIVE LOGITS
    AntiForgeryToken
    0.79
    withIdentifier
    0.67
     Request
    0.62
     Obtain
    0.60
     request
    0.58
     FetchType
    0.57
     GenerationType
    0.56
     Register
    0.56
    queryInterface
    0.56
     AssemblyCulture
    0.56
    Activations Density 0.004%

    No Known Activations