© 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. 97162
    Prev
    Next
    INDEX
    Explanations

    motivation and signals

    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
     incentive
    -2.23
     incentives
    -2.22
     Incentive
    -1.98
     Incentives
    -1.97
    Incenti
    -1.80
    incenti
    -1.77
     incentiv
    -1.48
     incenti
    -1.45
     reward
    -1.07
     Incenti
    -1.07
    POSITIVE LOGITS
    ClientSize
    0.57
    };*/
    0.54
    WebVitals
    0.53
    Попис
    0.49
    contentLoaded
    0.47
    ')));
    0.47
    *~*~
    0.46
    everywhere
    0.46
     createSprite
    0.46
     TestCase
    0.45
    Activations Density 0.117%

    No Known Activations