© 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. 45637
    Prev
    Next
    INDEX
    Explanations

    online writing and content

    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
     edition
    -0.48
    ization
    -0.47
    eader
    -0.47
     concept
    -0.46
    TagMode
    -0.46
     point
    -0.46
     thing
    -0.46
     issue
    -0.44
    허
    -0.44
    arische
    -0.43
    POSITIVE LOGITS
     of
    0.84
    RegistryLite
    0.66
    日閲覧
    0.65
     OnInit
    0.65
     kasarigan
    0.61
     useState
    0.57
     AssemblyTitle
    0.57
    oneofs
    0.57
    UrlResolution
    0.57
    ViewInit
    0.56
    Activations Density 0.091%

    No Known Activations