© 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. 4-CLT-HP
    7. 2658
    Prev
    Next
    INDEX
    Explanations

    both

    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
    ,
    -0.71
    +#+#
    -0.68
    $_['
    -0.57
     propOrder
    -0.53
    +:+
    -0.52
    WebElementEntity
    -0.50
    WaitGroup
    -0.49
     MonoBehaviour
    -0.49
     and
    -0.49
    quelize
    -0.48
    POSITIVE LOGITS
     internally
    0.75
     inside
    0.70
     externally
    0.67
     during
    0.66
     domestically
    0.66
     directly
    0.65
     onResponse
    0.64
     personally
    0.61
    directly
    0.60
     physically
    0.58
    Activations Density 0.006%

    No Known Activations