© 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. 4-CLT-HP
    7. 4914
    Prev
    Next
    INDEX
    Explanations

    this

    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
    parsedMessage
    -0.99
    WriteTagHelper
    -0.82
     nakalista
    -0.71
     mergeFrom
    -0.69
     >=",
    -0.69
    sizeCache
    -0.69
     "
    -0.67
    enterOuterAlt
    -0.66
     “
    -0.64
    PDOException
    -0.64
    POSITIVE LOGITS
     is
    0.77
     could
    0.75
     was
    0.69
     ensures
    0.59
     ensured
    0.59
     wasn
    0.56
     will
    0.55
     might
    0.55
     addresses
    0.55
     would
    0.50
    Activations Density 0.004%

    No Known Activations