© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 11712
    Prev
    Next
    INDEX
    Explanations

    science and medicine

    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
    \'
    -0.77
    ulsory
    -0.75
    SSS
    -0.69
    \'{
    -0.58
    \"
    -0.52
     tính
    -0.45
    villa
    -0.44
    Deal
    -0.44
    FRA
    -0.43
    {
    -0.43
    POSITIVE LOGITS
     Efq
    0.88
     Monfieur
    0.82
     chofe
    0.81
     Majefty
    0.80
    neſs
    0.79
     ſhould
    0.78
     fhew
    0.77
    ITERATURE
    0.76
     purpoſe
    0.75
    енча
    0.73
    Activations Density 0.044%

    No Known Activations