© 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. 20147
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the" in relation to various contexts or subjects

    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
    вр
    -0.47
     هستید
    -0.46
    ともに
    -0.45
    isNotBlank
    -0.45
     erheben
    -0.42
    共に
    -0.42
    ceive
    -0.42
    isAlive
    -0.42
    #!/
    -0.41
    ){}
    -0.41
    POSITIVE LOGITS
    migrationBuilder
    0.88
     CreateTagHelper
    0.86
    ########.
    0.73
     kasarigan
    0.71
     StatefulWidget
    0.71
    IUrlHelper
    0.71
    InstrumentedTest
    0.69
     مرئيه
    0.68
    ProgressHUD
    0.67
     oprot
    0.67
    Activations Density 0.061%

    No Known Activations