© 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. 4623
    Prev
    Next
    INDEX
    Explanations

    ably

    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
    mybatisplus
    -0.66
    :+:
    -0.65
    #+#
    -0.58
     surla
    -0.56
    出版年
    -0.55
     صوتيه
    -0.55
    endpush
    -0.54
    scriptId
    -0.52
    GOTREF
    -0.52
    تقاوى
    -0.52
    POSITIVE LOGITS
     nowhere
    0.59
    thâu
    0.52
     Pumping
    0.51
     something
    0.49
     Investing
    0.48
     Sickness
    0.48
     Signing
    0.48
     réguli
    0.48
     quelqu
    0.47
     someone
    0.47
    Activations Density 0.001%

    No Known Activations