© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 11362
    Prev
    Next
    INDEX
    Explanations

    the concept of slowing down

    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
     slowly
    -0.56
     gradual
    -0.56
    slowly
    -0.55
     Slowly
    -0.52
     réservé
    -0.51
     Wikimédia
    -0.50
     slow
    -0.50
     TestBed
    -0.49
    zeera
    -0.49
     Autorizaciones
    -0.49
    POSITIVE LOGITS
     slowing
    2.52
     slowed
    2.09
     slows
    1.84
     slowdown
    1.49
     deceleration
    1.28
     ralenti
    1.21
     deceler
    1.20
     rall
    0.78
    tagHelper
    0.73
     calmed
    0.70
    Activations Density 0.001%

    No Known Activations