© 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. 4-CLT-HP
    7. 3098
    Prev
    Next
    INDEX
    Explanations

    technical text

    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
     createContext
    -0.64
    PerformLayout
    -0.59
     raiſ
    -0.57
    createTextNode
    -0.57
     =>
    -0.54
     uſe
    -0.51
    infe
    -0.49
     fiume
    -0.49
     Intrinsic
    -0.48
    ?
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.59
    pushFollow
    0.58
    RTEX
    0.51
    writeField
    0.50
     kasarigan
    0.50
    تقاوى
    0.50
    Derbyniad
    0.48
    errHandler
    0.48
     cherchés
    0.48
     wenden
    0.48
    Activations Density 0.011%

    No Known Activations