© 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. 5-CLT-HP
    7. 2255
    Prev
    Next
    INDEX
    Explanations

    documents

    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
     فريبيس
    -0.51
     समीक्षाओं
    -0.49
     Италијани
    -0.44
    opt
    -0.40
    ::_('
    -0.40
     stället
    -0.39
    Part
    -0.38
    meliharaan
    -0.38
    limits
    -0.38
    untergang
    -0.38
    POSITIVE LOGITS
    indicato
    0.64
    uality
    0.62
     Volcanic
    0.60
    ETRIC
    0.57
    IVATE
    0.57
    verwijspagina
    0.57
    énario
    0.56
     BIBSYS
    0.55
     Devonshire
    0.55
    InSection
    0.55
    Activations Density 0.019%

    No Known Activations