© 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. 3249
    Prev
    Next
    INDEX
    Explanations

    sought

    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
    RegressionTest
    -0.83
    thâu
    -0.77
    MessageOf
    -0.74
     ApiException
    -0.73
     >=",
    -0.72
    theless
    -0.71
    SharedDtor
    -0.70
    PerformLayout
    -0.69
    ]--;
    -0.69
    ItemBackground
    -0.67
    POSITIVE LOGITS
     or
    0.68
     and
    0.66
    databind
    0.54
     ils
    0.52
    WebServlet
    0.49
    and
    0.47
    His
    0.46
     They
    0.46
     خارجية
    0.46
     inhoud
    0.45
    Activations Density 0.340%

    No Known Activations