© 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. 1-RES-MATRYOSHKA-DC
    7. 1293
    Prev
    Next
    INDEX
    Explanations

    sentences describing technical or conceptual difficulty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    newArrayList
    -0.68
     MonoBehaviour
    -0.62
    σκευ
    -0.52
    instant
    -0.50
    IMATE
    -0.50
     bờ
    -0.50
     soll
    -0.49
    τως
    -0.49
     estamp
    -0.48
    Instant
    -0.48
    POSITIVE LOGITS
     difficult
    3.70
    difficult
    3.58
     Difficult
    3.42
    Difficult
    3.27
     difícil
    2.67
     difficulty
    2.55
     challenging
    2.55
     difficile
    2.55
     difíciles
    2.55
     difficiles
    2.53
    Activations Density 0.332%

    No Known Activations