© 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. 3065
    Prev
    Next
    INDEX
    Explanations

    company names/legal entities

    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
     AdapterView
    -0.46
    StreetMap
    -0.44
     FontWeight
    -0.43
    /*!
    -0.43
    ghu
    -0.42
    ksh
    -0.41
     ===
    -0.41
     tiras
    -0.40
     ttk
    -0.40
    riages
    -0.39
    POSITIVE LOGITS
    ьаж
    0.78
     Roskov
    0.76
    tvguidetime
    0.70
     Réponses
    0.68
     ویکی‌پدی
    0.68
    petrol
    0.68
    CodedInputStream
    0.65
    StructEnd
    0.64
    Демографія
    0.61
    Petrol
    0.60
    Activations Density 0.009%

    No Known Activations