© 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. 6-RES-MATRYOSHKA-DC
    7. 1590
    Prev
    Next
    INDEX
    Explanations

    mentions of groups

    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
     étoile
    -0.67
     McE
    -0.62
    обходи
    -0.61
     Ull
    -0.61
    Aure
    -0.59
    ctor
    -0.59
    Ars
    -0.59
    locken
    -0.57
     Allende
    -0.57
    </
    -0.56
    POSITIVE LOGITS
     groups
    2.03
     Groups
    2.03
     group
    1.99
     getGroup
    1.88
     GROUP
    1.87
     Group
    1.85
    GROUP
    1.80
     GROUPS
    1.79
    groups
    1.74
    group
    1.73
    Activations Density 0.334%

    No Known Activations