© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1580
    Prev
    Next
    INDEX
    Explanations

    inflammation, TNF, cancer

    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
    tube
    -0.86
     exposing
    -0.74
     expose
    -0.67
     exposes
    -0.66
    Parcelize
    -0.62
    AndEndTag
    -0.61
    TN
    -0.59
    Tube
    -0.58
    ंदीखरीदारी
    -0.58
    MigrationBuilder
    -0.56
    POSITIVE LOGITS
    ()]);
    0.54
    '])
    
    0.53
    }")
    
    0.53
    "])
    
    0.52
    ++
    
    0.51
    ']
    
    0.51
    ']}
    0.51
    "];
    
    0.50
     Matériau
    0.50
    Dziękuję
    0.48
    Activations Density 0.339%

    No Known Activations