© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1952
    Prev
    Next
    INDEX
    Explanations

    code and markup languages

    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
     CanadaChoose
    -0.62
    ötz
    -0.59
    styleType
    -0.58
     Révolution
    -0.54
     romantique
    -0.52
    rostis
    -0.51
     ángeles
    -0.51
     throm
    -0.50
     PROGRAMME
    -0.50
    viewDidLoad
    -0.50
    POSITIVE LOGITS
     trade
    0.74
     AssemblyProduct
    0.62
    trade
    0.57
     Trade
    0.55
    Trade
    0.54
     trading
    0.54
    外部リンク
    0.53
     commerce
    0.53
     trades
    0.52
    CodedInputStream
    0.52
    Activations Density 0.001%

    No Known Activations