© 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. 5-CLT-HP
    7. 291
    Prev
    Next
    INDEX
    Explanations

    U.S

    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
     referenties
    -0.68
    IndentedString
    -0.66
     frames
    -0.63
     الحره
    -0.63
     charters
    -0.60
     drops
    -0.60
     drop
    -0.59
     driving
    -0.59
     drive
    -0.58
     sweet
    -0.57
    POSITIVE LOGITS
     églises
    0.64
     définiti
    0.59
     prisonniers
    0.58
     stället
    0.56
     IndexPath
    0.56
     genoux
    0.55
     négociations
    0.55
     varandra
    0.54
     vérit
    0.53
     courants
    0.52
    Activations Density 0.005%

    No Known Activations