© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 511
    Prev
    Next
    INDEX
    Explanations

    to

    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
     AssemblyTitle
    -0.60
     allegorical
    -0.58
     Teach
    -0.57
    Teach
    -0.56
     NTIS
    -0.54
    ItemBackground
    -0.53
    istice
    -0.52
     Obra
    -0.50
     teach
    -0.50
    rigkeit
    -0.50
    POSITIVE LOGITS
    bootstrapcdn
    0.69
    SequentialGroup
    0.67
     resourceCulture
    0.67
    awtextra
    0.62
    TagMode
    0.60
    Архівовано
    0.56
     الرياضيه
    0.55
     незавершена
    0.52
    MessageOf
    0.52
    mybatisplus
    0.52
    Activations Density 0.001%

    No Known Activations