© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 1476
    Prev
    Next
    INDEX
    Explanations

    words related to walking, physical activity, and rehabilitation

    oai_token-act-pair · gemini-2.0-flash
    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
     
    -0.66
     I
    -0.53
     to
    -0.52
     -
    -0.51
    ↵
    -0.51
     x
    -0.50
     X
    -0.49
     C
    -0.49
     a
    -0.48
     extra
    -0.48
    POSITIVE LOGITS
     defaultstate
    1.12
    ंदीखरीदारी
    1.01
    存于互联网档案馆
    0.97
    awtextra
    0.96
     pleaſure
    0.92
     كومونز
    0.89
    tagHelperRunner
    0.88
    ſelf
    0.88
    InjectAttribute
    0.88
     Posture
    0.86
    Activations Density 4.016%

    No Known Activations