© 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. 0-CLT-HP
    7. 92556
    Prev
    Next
    INDEX
    Explanations

    slow

    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
     slow
    -1.50
    Slow
    -1.43
     Slow
    -1.37
    slow
    -1.29
     SLOW
    -1.16
    SLOW
    -1.14
     mission
    -0.99
     missions
    -0.95
     slowest
    -0.94
     slowly
    -0.93
    POSITIVE LOGITS
    endphp
    0.65
    sun
    0.59
    dog
    0.57
    po
    0.56
    down
    0.56
    sing
    0.56
    s
    0.56
     LIRE
    0.55
    shot
    0.55
    варь
    0.55
    Activations Density 1.561%

    No Known Activations