© 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. 4-CLT-HP
    4. 2434
    Prev
    Next
    INDEX
    Explanations

    to

    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
     verhe
    -0.65
     förr
    -0.63
    ➞
    -0.60
     vítimas
    -0.60
     مرئيه
    -0.59
     excepción
    -0.59
     sitä
    -0.59
     slutet
    -0.59
     saken
    -0.58
     plomo
    -0.58
    POSITIVE LOGITS
     ModelExpression
    0.66
    клопе
    0.65
     agriculture
    0.53
     cleaning
    0.53
     arts
    0.52
    WriteTagHelper
    0.50
     aviation
    0.48
     healthcare
    0.48
     المعيارى
    0.47
     beginnetje
    0.47
    Activations Density 0.003%

    No Known Activations