© 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. 4-CLT-HP
    7. 1162
    Prev
    Next
    INDEX
    Explanations

    oropharynx

    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
    mpotent
    -0.56
    TestTools
    -0.55
    urably
    -0.50
    jstor
    -0.49
     onAnimation
    -0.48
     Bri
    -0.48
    Vidi
    -0.47
     innamor
    -0.47
    winn
    -0.47
    subplots
    -0.46
    POSITIVE LOGITS
    Välislingid
    0.61
    PageContext
    0.57
    EEG
    0.49
     avon
    0.48
    webElementXpaths
    0.47
     Ihm
    0.46
     joaat
    0.46
    DropTable
    0.45
    XmlSchema
    0.45
     SqlParameter
    0.45
    Activations Density 0.001%

    No Known Activations