© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15571
    Prev
    Next
    INDEX
    Explanations

    financial analysts or analyst-related terminology

    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
    TagHelper
    -0.64
     للاسماء
    -0.63
    ]--;
    -0.59
    Organisateur
    -0.59
    CrossRef
    -0.58
     Profession
    -0.56
    چه
    -0.55
     pedagogical
    -0.55
    ImageContext
    -0.55
    Carriera
    -0.53
    POSITIVE LOGITS
     analyst
    2.97
     Analyst
    2.73
     analysts
    2.67
    Analyst
    2.44
     Analysts
    2.44
    Analysts
    2.08
    analyst
    1.91
     pund
    0.91
     observers
    0.78
     commentator
    0.74
    Activations Density 0.001%

    No Known Activations