© 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. 5-CLT-HP
    7. 96790
    Prev
    Next
    INDEX
    Explanations

    industrial facilities

    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
     OnTrigger
    -0.55
    +#+#
    -0.50
    دانشنامهٔ
    -0.49
    期刊论文
    -0.48
    KEYCODE
    -0.48
     geslacht
    -0.47
     range
    -0.46
    serviceWorker
    -0.46
    printStackTrace
    -0.46
     match
    -0.45
    POSITIVE LOGITS
     utanför
    0.68
     scolaires
    0.61
     feroit
    0.60
     vermelhas
    0.60
    detectChanges
    0.60
     militaires
    0.57
     comigo
    0.57
     voisins
    0.56
     coupable
    0.55
     pouvoit
    0.55
    Activations Density 0.003%

    No Known Activations