© 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. 5-CLT-HP
    7. 97855
    Prev
    Next
    INDEX
    Explanations

    patients

    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
     hinweg
    -0.61
    AndEndTag
    -0.59
    ViewFeatures
    -0.56
    RegressionTest
    -0.55
    陆续
    -0.53
     befand
    -0.52
    PreferredItem
    -0.50
    httphttps
    -0.50
    Démographie
    -0.50
     selama
    -0.50
    POSITIVE LOGITS
     недавно
    0.65
     recently
    0.63
    recently
    0.60
     yesterday
    0.60
    yesterday
    0.59
     Yesterday
    0.59
     recent
    0.58
     tomorrow
    0.57
     вчера
    0.56
    recent
    0.56
    Activations Density 0.036%

    No Known Activations