© 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. 90884
    Prev
    Next
    INDEX
    Explanations

    religion and poverty

    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
     Paglinawan
    -0.69
     ddelweddau
    -0.58
    oprot
    -0.54
    Chham
    -0.53
     pinulongan
    -0.53
    Cyfeiriadau
    -0.52
     himo
    -0.52
    bloc
    -0.52
     defaultstate
    -0.52
     betweenstory
    -0.51
    POSITIVE LOGITS
    NewUrlParser
    0.58
    yntaxException
    0.56
     AssemblyCompany
    0.52
    безпе
    0.51
    basicConfig
    0.50
     humaine
    0.49
    styleType
    0.49
     Sociale
    0.49
     humano
    0.49
    physic
    0.48
    Activations Density 0.085%

    No Known Activations