© 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. 0-CLT-HP
    7. 1658
    Prev
    Next
    INDEX
    Explanations

    difficult/unexpected situations

    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
     circumstances
    -0.79
     Circumstances
    -0.64
     suddenly
    -0.59
     Unexpected
    -0.57
    Bains
    -0.57
     unexpectedly
    -0.54
     circonstances
    -0.52
    unexpected
    -0.51
    circum
    -0.51
    Unexpected
    -0.48
    POSITIVE LOGITS
    AccessorTable
    0.73
     betweenstory
    0.71
    enumii
    0.70
     autorytatywna
    0.69
    ymce
    0.68
    styleType
    0.65
    SharedCtor
    0.65
     Савезне
    0.64
     propOrder
    0.63
    зулта
    0.63
    Activations Density 0.370%

    No Known Activations