© 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. 1-CLT-HP
    7. 910
    Prev
    Next
    INDEX
    Explanations

    to be

    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
     مشين
    -0.94
    AndEndTag
    -0.82
    sizeCache
    -0.80
    ########.
    -0.79
    awtextra
    -0.77
    StoreMessageInfo
    -0.77
    脚注の使い方
    -0.75
     BorderLayout
    -0.75
    تقاوى
    -0.73
    findpost
    -0.72
    POSITIVE LOGITS
     brought
    0.71
     caused
    0.63
     produced
    0.62
     changed
    0.59
     created
    0.56
     turned
    0.52
     released
    0.50
     maintained
    0.49
     modified
    0.49
     prevented
    0.49
    Activations Density 0.014%

    No Known Activations