© 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. 2-RES-MATRYOSHKA-DC
    7. 4491
    Prev
    Next
    INDEX
    Explanations

    references to the potential or ability to depend on or be able to perform something

    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
    could
    -0.78
     could
    -0.77
     Could
    -0.73
     tartalomajánló
    -0.69
    Could
    -0.67
     COULD
    -0.66
     imposible
    -0.56
    couldn
    -0.56
    =\{
    -0.54
    =<?
    -0.54
    POSITIVE LOGITS
    cdnjs
    0.66
    elernt
    0.59
     autorytatywna
    0.57
    WriteTagHelper
    0.57
    зулта
    0.56
     Chwiliwch
    0.55
    aarrggbb
    0.54
    rval
    0.54
     مشين
    0.53
    Bef
    0.53
    Activations Density 0.288%

    No Known Activations