© 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. 94561
    Prev
    Next
    INDEX
    Explanations

    sentence snippets

    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
     Wikimedijinoj
    -0.72
    ніципа
    -0.68
    ponses
    -0.62
    
    -0.59
    Portale
    -0.58
    RTLR
    -0.56
    íncia
    -0.54
    ⤹
    -0.54
     BorderSide
    -0.54
    ########.
    -0.53
    POSITIVE LOGITS
    awtextra
    0.76
    ConstraintMaker
    0.72
     initComponents
    0.60
    AddTagHelper
    0.59
    tanleria
    0.54
     ProtoMessage
    0.50
    SharedDtor
    0.50
     appreciate
    0.50
     EconPapers
    0.50
    XmlAccessorType
    0.49
    Activations Density 0.002%

    No Known Activations