© 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. 12-RES-MATRYOSHKA-DC
    7. 10250
    Prev
    Next
    INDEX
    Explanations

    Java-related programming constructs and configuration elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وث
    -0.56
     Vork
    -0.54
     colored
    -0.52
     presto
    -0.52
    Portail
    -0.51
    ════
    -0.51
     interval
    -0.49
    rell
    -0.49
     Ansch
    -0.49
    ียน
    -0.49
    POSITIVE LOGITS
    ]--;
    0.71
    Дереккөздер
    0.69
     חיצוניים
    0.66
     Italijanski
    0.66
    )}</
    0.66
    ValueGeneration
    0.65
     ویکی‌پدیای
    0.64
     CURLOPT
    0.63
    NUMX
    0.63
     للاسماء
    0.63
    Activations Density 0.016%

    No Known Activations