© 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. 45478
    Prev
    Next
    INDEX
    Explanations

    reporting/concluding

    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
    
    -0.59
    Cubit
    -0.56
    EndGlobalSection
    -0.52
    bootstrapcdn
    -0.50
    InjectAttribute
    -0.50
    ائج
    -0.50
    roskop
    -0.50
    رشف
    -0.49
    otheby
    -0.48
     beginnetje
    -0.47
    POSITIVE LOGITS
    noons
    0.57
     Bibles
    0.56
     myrtle
    0.54
     Hebrews
    0.54
     Savior
    0.53
     hymns
    0.52
     Messiah
    0.52
     worshi
    0.51
     Psalms
    0.51
    LEncoder
    0.51
    Activations Density 0.054%

    No Known Activations