© 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. 4631
    Prev
    Next
    INDEX
    Explanations

    building foundations

    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
    ppelin
    -0.58
    GEBURTSDATUM
    -0.49
     refroid
    -0.45
     všem
    -0.44
     règlement
    -0.43
    lenovo
    -0.43
     zdar
    -0.43
    jsxFileName
    -0.43
    requently
    -0.43
    RESUMO
    -0.42
    POSITIVE LOGITS
    migrationBuilder
    0.67
    ContentAlignment
    0.64
    SpringBootTest
    0.60
    ỡng
    0.60
    Архівовано
    0.57
     protoimpl
    0.55
    didSet
    0.55
    providedIn
    0.55
    XmlAccessType
    0.55
    LOY
    0.54
    Activations Density 0.006%

    No Known Activations