© 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. 5109
    Prev
    Next
    INDEX
    Explanations

    references to downward or descending movements or actions

    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
     too
    -0.49
     any
    -0.43
     some
    -0.42
    唆
    -0.42
     other
    -0.42
     however
    -0.39
     remarquer
    -0.38
     vux
    -0.38
     adulta
    -0.38
     šķ
    -0.37
    POSITIVE LOGITS
    AddTagHelper
    1.01
    URLException
    0.97
     تضيفلها
    0.96
     kasarigan
    0.94
     المعيارى
    0.92
    parsedMessage
    0.91
    Chham
    0.85
     '\\;'
    0.85
    CloseOperation
    0.84
     kaarangay
    0.81
    Activations Density 0.332%

    No Known Activations