© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93673
    Prev
    Next
    INDEX
    Explanations

    uncertainty and possibilities

    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
     تضيفلها
    -0.98
    ValueStyle
    -0.87
    WebVitals
    -0.78
    出版年
    -0.76
     PyTuple
    -0.76
     يتيمه
    -0.74
     ویکی‌پدیا
    -0.73
    kloped
    -0.73
    findpost
    -0.73
    AndEndTag
    -0.73
    POSITIVE LOGITS
     original
    0.56
     
    0.55
     worthy
    0.52
     worthless
    0.49
     deserve
    0.48
     entirety
    0.48
     no
    0.48
     unworthy
    0.47
     identical
    0.46
     perfect
    0.45
    Activations Density 0.000%

    No Known Activations