© 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. 4-CLT-HP
    4. 2248
    Prev
    Next
    INDEX
    Explanations

    PDF

    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
    IPAC
    -0.57
     Gand
    -0.54
    PropertyChanging
    -0.53
    ]--;
    -0.53
     poured
    -0.52
    بوابة
    -0.50
    PreferredItem
    -0.49
    DebuggerNonUser
    -0.49
    AsUp
    -0.49
     ***!
    -0.48
    POSITIVE LOGITS
     onCreateView
    0.58
     lenker
    0.53
     jadx
    0.52
    rinfo
    0.50
     jouets
    0.50
     rhestr
    0.48
    enaire
    0.47
     decía
    0.46
     Germ
    0.46
    cole
    0.45
    Activations Density 0.002%

    No Known Activations