© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    expressions of reasoning or explanations for the difficulty of certain tasks

    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
     <<<<<<<<<<<<<<
    -0.83
     UIAlert
    -0.66
    ItemLayout
    -0.66
     tartalomajánló
    -0.64
     doInBackground
    -0.64
     bParam
    -0.62
     Nani
    -0.60
     createState
    -0.58
     facie
    -0.58
    ՚
    -0.58
    POSITIVE LOGITS
    省市镇
    0.54
    existsSync
    0.53
     then
    0.50
    #--
    0.49
    assertIn
    0.49
     zase
    0.48
    תוך
    0.48
    唯有
    0.48
     appunto
    0.47
    active
    0.47
    Activations Density 0.278%

    No Known Activations