© 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. 2420
    Prev
    Next
    INDEX
    Explanations

    references to the word "po" and its variations, often used as a prefix or part of words related to polling, posts, or topics in various languages

    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
    polar
    -1.00
     polarization
    -0.98
     polar
    -0.91
     polarized
    -0.88
    pol
    -0.82
    Polar
    -0.82
     pool
    -0.82
     Polar
    -0.81
    pool
    -0.81
     pools
    -0.77
    POSITIVE LOGITS
     po
    2.67
     Po
    2.14
    po
    2.02
    Po
    1.91
     PO
    1.62
    PO
    1.58
     Popper
    1.07
     Pok
    0.97
     poaching
    0.92
    popper
    0.87
    Activations Density 0.015%

    No Known Activations