© 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. 1530
    Prev
    Next
    INDEX
    Explanations

    science and research

    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
    nologies
    -0.87
     purpoſe
    -0.87
     BorderRadius
    -0.85
     Houſe
    -0.82
     greateſt
    -0.81
     neceffary
    -0.79
     houſe
    -0.79
     Majefty
    -0.78
     fubject
    -0.78
     beſt
    -0.77
    POSITIVE LOGITS
    <bos>
    0.56
     HttpHeaders
    0.45
     Ruck
    0.45
    accharide
    0.45
    existsSync
    0.45
     anteced
    0.44
     AssemblyProduct
    0.43
     cen
    0.43
     Wilk
    0.43
     […]
    0.42
    Activations Density 0.089%

    No Known Activations