© 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. 5-CLT-HP
    7. 96889
    Prev
    Next
    INDEX
    Explanations

    How someone is doing

    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
     AssemblyProduct
    -0.48
     bonfire
    -0.47
     Nomenclature
    -0.47
     what
    -0.45
    chemy
    -0.44
    dymyr
    -0.44
    annu
    -0.44
    allin
    -0.43
     Domain
    -0.43
     something
    -0.41
    POSITIVE LOGITS
     '\\;'
    0.76
    তথ্যসূত্র
    0.67
    原始内容存档于
    0.64
    İstinadlar
    0.62
    MigrationBuilder
    0.62
    Viited
    0.61
     snippetHide
    0.61
    انيف
    0.61
    ghest
    0.60
     ProtoMessage
    0.60
    Activations Density 0.003%

    No Known Activations