© 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. 2-RES-MATRYOSHKA-DC
    7. 3906
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of vehicle acceleration or deceleration

    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
     quickly
    -0.73
     grow
    -0.58
     quick
    -0.57
    oughby
    -0.57
    formik
    -0.57
    %)$
    -0.55
    Quickly
    -0.55
     QUICK
    -0.54
    quickly
    -0.54
     imme
    -0.54
    POSITIVE LOGITS
     acceleration
    2.97
     Acceleration
    2.69
    acceler
    2.52
    acceleration
    2.45
     acceler
    2.36
     accelerating
    2.36
    Acceler
    2.34
     Acceler
    2.30
    Acceleration
    2.28
     accelerate
    2.27
    Activations Density 0.012%

    No Known Activations