© 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. 0-CLT-HP
    7. 92400
    Prev
    Next
    INDEX
    Explanations

    Chemical processes and finance

    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
     finance
    -0.75
     face
    -0.73
     Chemical
    -0.64
     Finance
    -0.55
     FINANCE
    -0.50
    finance
    -0.48
    Finance
    -0.47
     j
    -0.47
     m
    -0.47
     CHEMICAL
    -0.47
    POSITIVE LOGITS
     itſelf
    1.13
     uſed
    1.01
     تانيه
    1.00
    
    1.00
     Houſe
    0.97
     AssemblyTitle
    0.95
     Shakspeare
    0.95
     ſmall
    0.94
     purpoſe
    0.93
     houſe
    0.93
    Activations Density 0.285%

    No Known Activations