© 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. 4-CLT-HP
    7. 1730
    Prev
    Next
    INDEX
    Explanations

    conjunctions

    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
    RegistryLite
    -0.48
    CELLANEOUS
    -0.48
     övers
    -0.47
    τώ
    -0.47
    الحياه
    -0.46
    MigrationBuilder
    -0.46
    zeß
    -0.44
    Välislingid
    -0.44
    ObjectContext
    -0.43
     noy
    -0.43
    POSITIVE LOGITS
     in
    1.60
     dalam
    1.05
     on
    0.96
     throughout
    0.94
    日在
    0.93
     within
    0.92
     elsewhere
    0.89
    ใน
    0.83
    dalam
    0.82
     through
    0.79
    Activations Density 0.015%

    No Known Activations