© 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. 4-CLT-HP
    7. 2040
    Prev
    Next
    INDEX
    Explanations

    code

    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
    Mutagenicity
    -0.54
    ÊN
    -0.49
    contentLoaded
    -0.49
     Wiseman
    -0.48
    RegressionTest
    -0.48
     Taf
    -0.47
    calipsis
    -0.47
    vacy
    -0.46
    laka
    -0.46
    Taf
    -0.46
    POSITIVE LOGITS
    iota
    0.63
     MainAxisSize
    0.63
    Билгалдахарш
    0.63
    iology
    0.63
    iolo
    0.58
     تانيه
    0.57
    cork
    0.55
    IOLOGY
    0.54
     Kela
    0.54
     Cio
    0.54
    Activations Density 0.002%

    No Known Activations