© 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. 0-RES-MATRYOSHKA-DC
    7. 12265
    Prev
    Next
    INDEX
    Explanations

    functions that evaluate and compare the expected utilities or values in decision-making models, particularly involving choice probabilities based on utility comparisons

    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
    JC
    -0.85
     متعلقه
    -0.74
     JC
    -0.61
    tagHelperRunner
    -0.61
     CreateTagHelper
    -0.60
    IBOutlet
    -0.57
     utafitiHapana
    -0.57
    tocin
    -0.55
     مرئيه
    -0.55
     noDo
    -0.54
    POSITIVE LOGITS
    jl
    1.84
    jc
    1.00
    jf
    0.99
    jt
    0.98
    jm
    0.85
    jg
    0.77
    jgl
    0.73
    jr
    0.66
    σθαι
    0.63
     jl
    0.61
    Activations Density 0.002%

    No Known Activations