© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72735
    Prev
    Next
    INDEX
    Explanations

    Incomplete sentences

    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
    각주
    -0.52
     חיצוניים
    -0.50
     are
    -0.50
    Vedi
    -0.49
    Were
    -0.49
    Referencies
    -0.49
     للاسماء
    -0.49
     were
    -0.48
     See
    -0.48
     Were
    -0.47
    POSITIVE LOGITS
     healed
    0.80
     propOrder
    0.78
     restored
    0.74
     levelled
    0.73
     cleaned
    0.72
     raised
    0.72
     cleared
    0.71
     leveled
    0.71
     left
    0.69
     rinsed
    0.69
    Activations Density 0.000%

    No Known Activations