© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    references to the capability or ability of a device, material, or molecular agent

    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
     विश्वसनीयता
    -0.65
     reda
    -0.52
    到的
    -0.52
    bor
    -0.51
    Obrigado
    -0.51
    ledem
    -0.51
     perturbed
    -0.50
    Obrigada
    -0.50
    af
    -0.49
    usermodel
    -0.48
    POSITIVE LOGITS
     capable
    2.69
    capable
    2.39
     capability
    1.63
     capables
    1.60
     incapable
    1.57
     Capability
    1.57
     capaces
    1.55
    capability
    1.55
     capaz
    1.52
     capace
    1.50
    Activations Density 0.013%

    No Known Activations