© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    ugs

    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
     from
    -0.63
    homa
    -0.60
     by
    -0.59
    ugs
    -0.58
     throughout
    -0.56
     populate
    -0.54
     iz
    -0.54
     AI
    -0.53
     sed
    -0.52
     AL
    -0.51
    POSITIVE LOGITS
     espirituales
    0.84
     виправивши
    0.84
     AssemblyCompany
    0.81
     kasarigan
    0.78
     Мексичка
    0.75
     définiti
    0.70
     fieldNum
    0.69
     Theſe
    0.68
    berdayakan
    0.68
     feroit
    0.67
    Activations Density 0.350%

    No Known Activations