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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15487
    Prev
    Next
    INDEX
    Explanations

    references to software package files, specifically the word "jar" and variations thereof

    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
    rceil
    -0.56
     ujednoznacz
    -0.54
    たくない
    -0.54
     ImGui
    -0.53
     happiest
    -0.52
     jsPsych
    -0.50
    abon
    -0.50
     gezond
    -0.50
    ChildScrollView
    -0.49
     happier
    -0.49
    POSITIVE LOGITS
    jar
    3.02
    JAR
    1.75
    jars
    1.12
    jara
    1.01
    jari
    0.97
    jarse
    0.86
    Jar
    0.84
    jaran
    0.83
    verwijspagina
    0.77
    jare
    0.75
    Activations Density 0.001%

    No Known Activations