© 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. 5537
    Prev
    Next
    INDEX
    Explanations

    specific bitwise flag conditions in code

    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
     ujednoznacz
    -0.57
    ''')
    -0.49
    ⁢
    -0.45
     community
    -0.45
    lik
    -0.43
    fclose
    -0.43
    atimes
    -0.43
    würdig
    -0.42
     NavController
    -0.42
    GeoNames
    -0.42
    POSITIVE LOGITS
    MSK
    1.17
    #+#
    0.84
     |=
    0.76
     médicaux
    0.71
     picioare
    0.68
    +#+
    0.66
     ISNI
    0.64
    bitset
    0.64
     Jefus
    0.64
     Bress
    0.63
    Activations Density 0.430%

    No Known Activations