© 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. 5-CLT-HP
    7. 2955
    Prev
    Next
    INDEX
    Explanations

    Observation and code snippets

    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
    بوابة
    -0.68
    Obrázky
    -0.62
    clusal
    -0.60
    BASEPATH
    -0.60
    weile
    -0.57
    styleType
    -0.53
    ίναι
    -0.53
    invokeLater
    -0.52
    prins
    -0.51
    AutoField
    -0.51
    POSITIVE LOGITS
    jsonwebtoken
    0.58
    userdetails
    0.57
    SceneManagement
    0.50
    longValue
    0.50
    клопе
    0.49
    EXPECT
    0.47
    CommandText
    0.46
     noastre
    0.46
     ledit
    0.45
    PYX
    0.45
    Activations Density 0.006%

    No Known Activations