© 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. 2-RES-MATRYOSHKA-DC
    7. 2484
    Prev
    Next
    INDEX
    Explanations

    references to ground or ground-related materials involving ground or grounding substances

    oai_token-act-pair · gpt-4.1-nano
    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
     بيها
    -0.83
     '\\;'
    -0.77
     Roskov
    -0.75
    WithIOException
    -0.73
     насељу
    -0.72
    AndEndTag
    -0.71
    aarrggbb
    -0.69
    ValueStyle
    -0.69
     muualla
    -0.69
     kaarangay
    -0.69
    POSITIVE LOGITS
     ground
    4.22
     Ground
    3.89
    ground
    3.84
    Ground
    3.84
     GROUND
    3.70
    GROUND
    3.28
     Grounds
    2.58
     grounds
    2.52
    grounds
    2.44
     grond
    1.95
    Activations Density 0.091%

    No Known Activations