© 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. 96701
    Prev
    Next
    INDEX
    Explanations

    one

    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
    StructEnd
    -0.56
     OFDb
    -0.52
     censiti
    -0.51
    protoimpl
    -0.51
     متعلقه
    -0.50
    уда
    -0.47
     unknownFields
    -0.47
    LookAnd
    -0.47
    pie
    -0.47
     onOptions
    -0.45
    POSITIVE LOGITS
     gioielli
    0.68
    AnimationsModule
    0.66
     debout
    0.65
     disparu
    0.58
    Архівовано
    0.56
     chré
    0.56
     librement
    0.55
     venons
    0.55
     marié
    0.55
     avoient
    0.55
    Activations Density 0.008%

    No Known Activations