© 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. 94672
    Prev
    Next
    INDEX
    Explanations

    License

    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
    الدراسه
    -0.81
    tanleria
    -0.69
     continúas
    -0.66
     PyLong
    -0.66
     Yorkers
    -0.63
    RegressionTest
    -0.62
    selbe
    -0.62
     Persons
    -0.60
    ftagPool
    -0.59
    Notae
    -0.59
    POSITIVE LOGITS
    onOptions
    0.57
    __":
    0.50
    testify
    0.46
     sympy
    0.45
    ändern
    0.44
    ContentAsync
    0.43
    __":
    0.42
    __':
    0.41
     GenerationType
    0.40
    globalData
    0.40
    Activations Density 0.064%

    No Known Activations