© 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. 40588
    Prev
    Next
    INDEX
    Explanations

    product

    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
    astify
    -0.60
    product
    -0.56
    hofer
    -0.56
    Product
    -0.54
     تضيفلها
    -0.54
     products
    -0.54
    avaient
    -0.54
     consultato
    -0.53
    YLON
    -0.53
    ณา
    -0.53
    POSITIVE LOGITS
     Bioaccumulative
    0.63
    unmodifiable
    0.56
    ulemon
    0.54
    SourceChecksum
    0.54
     Wikispecies
    0.53
     calendriers
    0.50
    pidou
    0.49
    Bioaccumulative
    0.49
     calculées
    0.48
     becauſe
    0.48
    Activations Density 0.059%

    No Known Activations