© 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. 3925
    Prev
    Next
    INDEX
    Explanations

    references to high cost or expense

    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
     oprot
    -0.75
    ReusableCell
    -0.60
    simeq
    -0.59
    edoria
    -0.57
     thym
    -0.57
    ruitt
    -0.57
     laine
    -0.56
    ligible
    -0.56
    drawable
    -0.55
     vecka
    -0.55
    POSITIVE LOGITS
     expensive
    2.78
     Expensive
    2.42
    expensive
    2.42
    Expensive
    2.20
     costly
    2.09
     pricey
    2.08
     дорого
    1.58
     caros
    1.40
     teuer
    1.34
     дорогие
    1.25
    Activations Density 0.011%

    No Known Activations