© 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. 1-CLT-HP
    7. 570
    Prev
    Next
    INDEX
    Explanations

    begin

    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
     للمعارف
    -0.66
     سكانية
    -0.66
     AssemblyCulture
    -0.53
    zembro
    -0.53
    WebElementEntity
    -0.52
    мум
    -0.51
    ghalaya
    -0.51
    sego
    -0.50
    poran
    -0.49
    HomeAsUpEnabled
    -0.49
    POSITIVE LOGITS
    findpost
    0.82
    Yok
    0.60
    featureID
    0.57
     pinulongan
    0.56
    keyColumn
    0.55
    InitVars
    0.55
     старости
    0.53
    phylo
    0.52
    ológicos
    0.52
     Idy
    0.50
    Activations Density 0.160%

    No Known Activations