© 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. 0-RES-MATRYOSHKA-DC
    7. 12886
    Prev
    Next
    INDEX
    Explanations

    references to the specific term "Jar" in various contexts

    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
     môi
    -0.68
    getSimpleName
    -0.59
    ندر
    -0.54
    lccccc
    -0.52
    Maur
    -0.52
    حياتها
    -0.51
     contenu
    -0.51
     Devan
    -0.51
     kade
    -0.50
    acamole
    -0.50
    POSITIVE LOGITS
     Jar
    2.73
     jar
    2.67
    Jar
    2.36
     jars
    2.13
     JAR
    1.88
     Jars
    1.84
     Jarrett
    1.02
    jars
    0.97
    JAR
    0.94
     Jarvis
    0.94
    Activations Density 0.002%

    No Known Activations