© 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. 7104
    Prev
    Next
    INDEX
    Explanations

    references to Java programming language in code-related 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
     ModelExpression
    -0.89
     android
    -0.84
    android
    -0.74
    AccessorTable
    -0.71
     Android
    -0.63
     resourceCulture
    -0.63
    ANDROID
    -0.59
    resizingMask
    -0.59
     php
    -0.57
    Biographie
    -0.56
    POSITIVE LOGITS
    java
    1.87
    google
    0.72
    Google
    0.72
     Google
    0.71
     ✭✭
    0.67
    DebuggerNonUser
    0.58
    googleapis
    0.56
    GOOGLE
    0.55
     google
    0.55
    gines
    0.53
    Activations Density 0.005%

    No Known Activations