© 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. 4-CLT-HP
    7. 3159
    Prev
    Next
    INDEX
    Explanations

    methane

    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
     utafitiHapana
    -0.78
    
    -0.65
    CppMethod
    -0.63
    urlpatterns
    -0.62
     Meksiku
    -0.62
     Wikispecies
    -0.62
     doInBackground
    -0.59
     ویکی‌پدیا
    -0.59
     ویکی‌آمباردا
    -0.59
    ngOnInit
    -0.59
    POSITIVE LOGITS
    Gön
    0.50
     preocupes
    0.42
     mouseY
    0.41
    Fair
    0.41
     تانيه
    0.41
    FORE
    0.39
    چھ
    0.39
    écou
    0.39
     MCS
    0.38
    ρών
    0.38
    Activations Density 0.016%

    No Known Activations