© 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. 1-RES-MATRYOSHKA-DC
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    references to a predominant or central role

    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
    Not in Any Lists

    No Comments

    Negative Logits
     zelfs
    -0.92
     dokonce
    -0.81
    Personendaten
    -0.81
     חיצוניים
    -0.77
     sogar
    -0.77
    جوايز
    -0.75
     myö
    -0.71
     unexpectedly
    -0.70
     even
    -0.68
     dessutom
    -0.68
    POSITIVE LOGITS
     mainly
    3.72
     primarily
    3.58
     mostly
    3.45
     Mainly
    3.45
    primarily
    3.30
     Mostly
    3.28
    mainly
    3.25
    mostly
    3.17
    Mostly
    3.17
    Mainly
    3.16
    Activations Density 0.267%

    No Known Activations