© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 181
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating location or positioning

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    NameValuePair
    -0.56
    addCriterion
    -0.53
    DockStyle
    -0.51
     resourceCulture
    -0.51
    ReusableCell
    -0.50
    AnimationsModule
    -0.49
     actionBar
    -0.48
     NavController
    -0.47
     EconPapers
    -0.47
    JspWriter
    -0.46
    POSITIVE LOGITS
     it
    1.12
     It
    1.03
    它
    0.98
    It
    0.90
     its
    0.88
     它
    0.87
     Its
    0.81
    Its
    0.80
     Itself
    0.76
    它是
    0.74
    Activations Density 1.511%

    No Known Activations