© 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. 2-RES-MATRYOSHKA-DC
    7. 5442
    Prev
    Next
    INDEX
    Explanations

    references to legal rulings or instances of a case "falling" within a specific context

    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
     down
    -0.76
    down
    -0.58
     Down
    -0.52
     kasarigan
    -0.52
     DOWN
    -0.50
    abetes
    -0.49
     comand
    -0.49
    contentValues
    -0.48
    Down
    -0.48
     dou
    -0.47
    POSITIVE LOGITS
     fall
    3.67
    fall
    3.31
     Fall
    3.25
    Fall
    3.25
     FALL
    3.16
    FALL
    3.13
     falls
    3.03
    falls
    2.91
     falling
    2.72
    falling
    2.66
    Activations Density 0.050%

    No Known Activations