© 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. 41012
    Prev
    Next
    INDEX
    Explanations

    medical/technical contexts

    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
     diaphragm
    -0.81
     ſeveral
    -0.76
     photolibrary
    -0.76
     itſelf
    -0.74
     Shakspeare
    -0.74
     Monfieur
    -0.71
     Reſ
    -0.70
     Diſ
    -0.70
    principalTable
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
    /**
    0.57
     My
    0.52
    sma
    0.51
    /***/
    0.50
     my
    0.50
     South
    0.50
     Inc
    0.49
     i
    0.49
     au
    0.48
     @
    0.47
    Activations Density 0.047%

    No Known Activations