© 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. 45543
    Prev
    Next
    INDEX
    Explanations

    time or seasons

    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
    ,
    -0.66
     fall
    -0.56
    MessageOf
    -0.56
     "
    -0.52
     spring
    -0.52
    SourceChecksum
    -0.50
     (
    -0.50
     and
    -0.47
      
    -0.46
     bet
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.79
     ſeveral
    0.78
     Majefty
    0.77
     Diſ
    0.76
     Efq
    0.76
     ſtate
    0.76
     uſ
    0.75
     Eſ
    0.74
     ſmall
    0.74
     faſt
    0.74
    Activations Density 0.142%

    No Known Activations