© 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. 12341
    Prev
    Next
    INDEX
    Explanations

    references to mortgage or mortgage-related financial terms

    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
     zucchero
    -0.57
    Interop
    -0.54
     Lerner
    -0.53
     fantasia
    -0.51
     Corbett
    -0.50
     oph
    -0.49
    thaler
    -0.48
     Thorpe
    -0.47
    copically
    -0.47
    dataclass
    -0.47
    POSITIVE LOGITS
    mort
    2.06
     mort
    1.87
     Mort
    1.86
    Mort
    1.73
     MORT
    1.38
     mortgages
    1.29
     mortgage
    1.27
     Mortgage
    1.23
    Mortgage
    1.08
    mortgage
    1.08
    Activations Density 0.004%

    No Known Activations