© 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. 0-RES-MATRYOSHKA-DC
    7. 10487
    Prev
    Next
    INDEX
    Explanations

    instances of confirmed scientific findings or results

    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
     affirm
    -1.09
    affirm
    -0.94
     verify
    -0.86
     affirmation
    -0.85
     verification
    -0.79
     verifier
    -0.78
     affirming
    -0.77
     affirms
    -0.76
     validate
    -0.75
     verifying
    -0.75
    POSITIVE LOGITS
     confirmed
    1.27
    confirmed
    1.10
     Confirmed
    1.09
    Confirmed
    0.91
     confirmado
    0.71
     confirmé
    0.60
     reposer
    0.58
    Réponse
    0.54
    どうやら
    0.53
     announced
    0.52
    Activations Density 0.005%

    No Known Activations