© 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. 93332
    Prev
    Next
    INDEX
    Explanations

    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
    spyOn
    -0.59
     growth
    -0.55
     trần
    -0.51
    ocytic
    -0.51
    ÓS
    -0.50
     nahilalakip
    -0.50
    IMENTO
    -0.50
     detection
    -0.48
    glycemia
    -0.47
     su
    -0.44
    POSITIVE LOGITS
     виправивши
    0.73
     resourceCulture
    0.67
    fjspx
    0.66
     cérémonie
    0.61
    Tembelea
    0.60
     medlemmer
    0.59
    hoeddwyd
    0.58
    InjectAttribute
    0.57
     coû
    0.57
     AssemblyCompany
    0.56
    Activations Density 0.005%

    No Known Activations