© 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. 0-CLT-HP
    7. 41440
    Prev
    Next
    INDEX
    Explanations

    gaming

    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
    hoea
    -0.65
    पया
    -0.63
    ThroughAttribute
    -0.61
     EconPapers
    -0.61
     للمعارف
    -0.61
    المناصب
    -0.57
    WithIOException
    -0.57
     HttpNotFound
    -0.57
    BufferException
    -0.56
    ///</
    -0.56
    POSITIVE LOGITS
    izeit
    0.57
     mộ
    0.52
     voices
    0.50
     betweenstory
    0.48
    lily
    0.47
     papilla
    0.47
     footsteps
    0.47
     iload
    0.47
    nals
    0.47
    werb
    0.47
    Activations Density 0.142%

    No Known Activations