© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    references to financial expenditures or costs

    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
     ImageIcon
    -0.57
     actual
    -0.56
    actual
    -0.53
    oprene
    -0.53
     entire
    -0.50
    zarchiwizowane
    -0.49
    opter
    -0.48
     Coruña
    -0.48
    WidgetItem
    -0.47
     exact
    -0.47
    POSITIVE LOGITS
     totaling
    2.36
     totalling
    2.09
     amounting
    1.88
     totaled
    1.73
     totalled
    1.54
     totals
    1.52
     amounted
    1.46
     averages
    1.13
     numbering
    1.05
     Totals
    0.98
    Activations Density 0.002%

    No Known Activations