© 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. 2926
    Prev
    Next
    INDEX
    Explanations

    relative pronouns

    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
    
    -0.80
    XmlAccessType
    -0.66
    oa̍t
    -0.59
    ⓧ
    -0.58
     courir
    -0.54
    contentLoaded
    -0.54
     confronti
    -0.52
    脚注の使い方
    -0.52
    AddTagHelper
    -0.52
    TagHelper
    -0.52
    POSITIVE LOGITS
     man
    0.70
     He
    0.59
    atorics
    0.56
     omnia
    0.56
    lossians
    0.53
    fony
    0.51
     issues
    0.51
     grounds
    0.51
     nothing
    0.51
     Man
    0.51
    Activations Density 0.002%

    No Known Activations