© 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. 41102
    Prev
    Next
    INDEX
    Explanations

    historically

    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
     historically
    -1.55
     Historically
    -1.27
     Telescope
    -1.11
    Historically
    -1.10
     histórica
    -1.06
     historical
    -0.97
     historique
    -0.96
     traditionally
    -0.90
     históricas
    -0.90
    histor
    -0.90
    POSITIVE LOGITS
    ArgsConstructor
    0.48
    ist
    0.43
    ாள
    0.42
    зонта
    0.41
    rowCount
    0.41
    ih
    0.40
    wal
    0.40
    ia
    0.40
     thân
    0.40
     Constructed
    0.39
    Activations Density 0.116%

    No Known Activations