© 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. 20-CLT-HP
    7. 73773
    Prev
    Next
    INDEX
    Explanations

    order/position

    np_max-act-logits · 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
    PerformLayout
    -0.79
    ArrowToggle
    -0.75
     DEVELOPMENT
    -0.75
    enumi
    -0.74
    Development
    -0.72
     estekak
    -0.71
     &___
    -0.69
     transfieras
    -0.69
    PreferredItem
    -0.69
    RegistryLite
    -0.69
    POSITIVE LOGITS
     L
    0.55
     first
    0.47
     BR
    0.46
     less
    0.46
     emerging
    0.46
     under
    0.45
     upper
    0.45
     fast
    0.43
     rapidly
    0.43
     middle
    0.42
    Activations Density 0.000%

    No Known Activations