© 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-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 3228
    Prev
    Next
    INDEX
    Explanations

    the word "near".

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     distance
    -0.80
     distances
    -0.77
     Close
    -0.75
     Distance
    -0.74
    Close
    -0.74
     closes
    -0.74
    closer
    -0.74
     distanced
    -0.74
    closes
    -0.72
     afstand
    -0.70
    POSITIVE LOGITS
     near
    2.38
    near
    2.25
     Near
    2.06
    Near
    2.06
     NEAR
    1.74
    NEAR
    1.45
     возле
    0.94
     nears
    0.92
     neer
    0.92
     cerca
    0.89
    Activations Density 0.007%

    No Known Activations