© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-RES-MATRYOSHKA-DC
    7. 4147
    Prev
    Next
    INDEX
    Explanations

    references to financial funds or the word "fund" in various contexts

    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
    ########.
    -0.65
     Financial
    -0.64
     Edg
    -0.55
     financial
    -0.54
    Financial
    -0.54
    Referanser
    -0.54
    ApiModelProperty
    -0.54
     bờ
    -0.49
     skjø
    -0.48
    financial
    -0.48
    POSITIVE LOGITS
     fund
    3.63
     Fund
    3.59
    Fund
    3.33
    fund
    3.25
     FUND
    3.16
    FUND
    2.95
     Funds
    2.33
    funds
    2.16
    Funds
    2.09
     FUNDS
    2.06
    Activations Density 0.019%

    No Known Activations