© 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. 0-CLT-HP
    4. 90862
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific texts, HTML tags

    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
    ularia
    -1.23
    ambar
    -0.81
    lossus
    -0.71
    fractive
    -0.70
    vious
    -0.66
    ]++;
    -0.61
     intptr
    -0.61
    bigoplus
    -0.52
    pyx
    -0.51
     onBackPressed
    -0.50
    POSITIVE LOGITS
     mécan
    0.55
     évalu
    0.55
     présidenti
    0.52
     régions
    0.52
     chargés
    0.52
     regioni
    0.51
     juridiques
    0.51
    تقاوى
    0.50
    nessy
    0.50
     carico
    0.50
    Activations Density 0.347%

    No Known Activations