© 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. 0-CLT-HP
    7. 94135
    Prev
    Next
    INDEX
    Explanations

    complement/baseline

    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
     complement
    -0.66
    iti
    -0.53
    Filed
    -0.52
    InSection
    -0.52
    Clik
    -0.51
    Напомним
    -0.51
     baseline
    -0.50
     AssemblyCulture
    -0.50
    itism
    -0.50
     complements
    -0.50
    POSITIVE LOGITS
     newBuilder
    0.82
    parsedMessage
    0.69
     useStyles
    0.65
    WireFormat
    0.59
     eater
    0.57
    chets
    0.57
     AssemblyProduct
    0.57
    GeneratedMessage
    0.57
    awtextra
    0.56
     fread
    0.56
    Activations Density 0.067%

    No Known Activations