© 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. 1-CLT-HP
    7. 10289
    Prev
    Next
    INDEX
    Explanations

    languages

    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
     Speaking
    -0.66
     Language
    -0.64
    migrationBuilder
    -0.60
     '\\;'
    -0.60
    speaking
    -0.59
    $_['
    -0.57
    MemoryWarning
    -0.57
     Phrases
    -0.57
    CppCodeGen
    -0.55
     word
    -0.55
    POSITIVE LOGITS
    Раз
    0.51
    ẻo
    0.48
    })*/
    0.48
     pprint
    0.46
    antaranya
    0.45
     województwie
    0.44
    ětí
    0.44
     contextLoads
    0.43
     reflectors
    0.42
     acoper
    0.41
    Activations Density 0.013%

    No Known Activations