© 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. 92228
    Prev
    Next
    INDEX
    Explanations

    investigation

    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
     investigation
    -0.65
     Investigation
    -0.64
    Investigation
    -0.64
     INVESTIGATION
    -0.60
     investigations
    -0.56
    investigation
    -0.56
    はじめに
    -0.54
    Study
    -0.53
     study
    -0.50
     estudio
    -0.50
    POSITIVE LOGITS
     myſelf
    0.87
     pleaſure
    0.86
     ſmall
    0.81
     uſ
    0.73
     itſelf
    0.72
     Efq
    0.71
     Monfieur
    0.71
     faſt
    0.70
     ſte
    0.69
     himſelf
    0.68
    Activations Density 0.038%

    No Known Activations