© 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. 11777
    Prev
    Next
    INDEX
    Explanations

    sea snails

    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
     So
    -0.40
     Be
    -0.39
     na
    -0.37
     Tr
    -0.37
    :
    -0.35
     ré
    -0.35
    )
    -0.34
    ↵
    -0.34
     gar
    -0.32
     plas
    -0.32
    POSITIVE LOGITS
     resourceCulture
    1.16
     Roskov
    1.09
    fjspx
    1.01
     EconPapers
    0.91
     Monfieur
    0.89
     propOrder
    0.87
    protoimpl
    0.86
     فريبيس
    0.86
     pauvreté
    0.85
     chi̍t
    0.85
    Activations Density 0.029%

    No Known Activations