© 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. 97836
    Prev
    Next
    INDEX
    Explanations

    they/their

    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
    siya
    -0.37
    thum
    -0.37
     id
    -0.34
     name
    -0.33
     I
    -0.32
    mn
    -0.32
     St
    -0.32
    groupBox
    -0.32
    amate
    -0.31
    ignty
    -0.31
    POSITIVE LOGITS
    ThroughAttribute
    0.98
    LookAnd
    0.98
    RegressionTest
    0.95
    SourceChecksum
    0.93
    XmlEnum
    0.92
     AssemblyCulture
    0.86
     betweenstory
    0.84
    principalTable
    0.82
    parsedMessage
    0.82
    ItemBackground
    0.82
    Activations Density 0.043%

    No Known Activations