© 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. 1-CLT-HP
    7. 11483
    Prev
    Next
    INDEX
    Explanations

    specialized texts

    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
     Record
    -0.61
     record
    -0.59
    +#+#
    -0.54
     ProtoMessage
    -0.54
    record
    -0.54
    Record
    -0.54
    eezy
    -0.51
    entery
    -0.51
    dė
    -0.50
    تقاوى
    -0.49
    POSITIVE LOGITS
    SequentialGroup
    0.62
    expandindo
    0.56
    MigrationBuilder
    0.55
    ificance
    0.54
     speech
    0.52
    èdent
    0.52
    出版年
    0.51
     Autónoma
    0.49
    ImageContext
    0.48
    FOL
    0.48
    Activations Density 0.035%

    No Known Activations