© 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. 4855
    Prev
    Next
    INDEX
    Explanations

    variety of contexts

    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
     Paglinawan
    -0.64
     saites
    -0.63
    principalColumn
    -0.56
    !*\
    -0.56
     createState
    -0.55
     MainAxisSize
    -0.54
    ObjectModel
    -0.53
    StoreMessageInfo
    -0.52
    ỡng
    -0.51
    .'"
    -0.51
    POSITIVE LOGITS
     kaarangay
    0.59
    ########.
    0.56
    StructEnd
    0.55
     Yeast
    0.53
     traduc
    0.51
     menschen
    0.51
    httphttps
    0.50
     embri
    0.49
    featureID
    0.48
     Wikispecies
    0.48
    Activations Density 0.023%

    No Known Activations