© 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. 2467
    Prev
    Next
    INDEX
    Explanations

    references to being physically lowered or descending

    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
     fall
    -0.97
    FALL
    -0.93
     FALL
    -0.92
     Fall
    -0.90
    Fall
    -0.89
    fall
    -0.87
     للاسماء
    -0.85
     falls
    -0.84
     falling
    -0.78
     Falling
    -0.78
    POSITIVE LOGITS
     down
    1.12
    down
    0.61
     DOWN
    0.58
    Down
    0.55
    DOWN
    0.53
    ocere
    0.53
    iteiten
    0.52
    vän
    0.51
    IUrlHelper
    0.50
    styleable
    0.49
    Activations Density 0.023%

    No Known Activations