© 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. 0-CLT-HP
    7. 90513
    Prev
    Next
    INDEX
    Explanations

    rome

    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
    ENE
    -0.81
    rops
    -0.68
    ROME
    -0.65
    rome
    -0.63
    otene
    -0.55
    참고
    -0.54
    GraphicsUnit
    -0.52
    bine
    -0.51
    Autoritní
    -0.51
     tänka
    -0.50
    POSITIVE LOGITS
    ########.
    0.69
    ValueStyle
    0.62
     שוליים
    0.60
     AssemblyVersion
    0.58
    !")
    0.57
    tably
    0.57
     EIS
    0.55
     Shakspeare
    0.55
    بوابة
    0.55
     curd
    0.55
    Activations Density 0.372%

    No Known Activations