© 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. 6-RES-MATRYOSHKA-DC
    7. 139
    Prev
    Next
    INDEX
    Explanations

    code containing `import` statements, `@` symbols and code relating to `android`

    oai_token-act-pair · gemini-2.0-flash
    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
     betweenstory
    -1.23
     ویکی‌پدی
    -1.21
    RegressionTest
    -1.15
    sizeCache
    -1.11
    NameInMap
    -1.10
    adpleegd
    -1.05
    :✨
    -1.05
    ⓧ
    -1.05
    InstrumentedTest
    -1.04
    contentLoaded
    -1.01
    POSITIVE LOGITS
     BoxDecoration
    1.03
    󠁢
    0.63
    prepareStatement
    0.60
    stretchr
    0.59
    databind
    0.57
    AxisAlignment
    0.56
    enumi
    0.56
    GHIJKLM
    0.55
    UIControlState
    0.55
    InstanceState
    0.52
    Activations Density 3.161%

    No Known Activations