© 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. 0-RES-MATRYOSHKA-DC
    7. 13222
    Prev
    Next
    INDEX
    Explanations

    representations of various currency symbols

    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
    AddTagHelper
    -0.57
    queous
    -0.52
    MergeFrom
    -0.51
    odine
    -0.50
     isInitialized
    -0.50
     Erişim
    -0.48
    bcryptjs
    -0.48
    onzo
    -0.47
     lpg
    -0.46
    initComponents
    -0.46
    POSITIVE LOGITS
    ZL
    2.08
    ZM
    1.80
    ZR
    1.77
    ZB
    1.70
    ZD
    1.40
    ZS
    1.38
    ZT
    1.25
    ZK
    1.20
    ZH
    1.17
    zr
    1.14
    Activations Density 0.004%

    No Known Activations