© 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. 22-RES-MATRYOSHKA-DC
    7. 1613
    Prev
    Next
    INDEX
    Explanations

    the word "test" in a programming context, as well as "test" used as verb

    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/blocks.22.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.22.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
    Obrázky
    -0.62
    OCCURRED
    -0.60
    cloudfront
    -0.58
     كومونز
    -0.58
    DockStyle
    -0.58
    Réponse
    -0.56
    Solved
    -0.55
    Решение
    -0.53
    клопе
    -0.53
    balleur
    -0.52
    POSITIVE LOGITS
     test
    3.27
     testing
    2.91
     tests
    2.83
     Test
    2.78
    test
    2.61
    Test
    2.61
     TEST
    2.56
     Testing
    2.55
     Tests
    2.42
     tested
    2.38
    Activations Density 2.198%

    No Known Activations