© 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. 1380
    Prev
    Next
    INDEX
    Explanations

    an assortment of common words and parts of words, seemingly without a clear pattern

    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
    الحياه
    -0.83
     shrimps
    -0.74
     advices
    -0.69
     infos
    -0.65
     defa
    -0.64
    Basta
    -0.64
     envisaged
    -0.62
     Premises
    -0.60
     Nowadays
    -0.59
     scanty
    -0.59
    POSITIVE LOGITS
     aren
    0.72
     preventative
    0.72
    Whilst
    0.71
     querr
    0.71
    Pictured
    0.71
     whilst
    0.68
     furthering
    0.65
    Additionally
    0.62
    TELL
    0.62
     monies
    0.61
    Activations Density 10.075%

    No Known Activations