© 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. 31092
    Prev
    Next
    INDEX
    Explanations

    occurrences of the definite article "the."

    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
     apă
    -0.60
    شهاد
    -0.59
     piele
    -0.52
     ThemeData
    -0.52
    !
    -0.52
     réguli
    -0.51
     mxArray
    -0.51
    cap
    -0.50
    zydent
    -0.50
    完整的
    -0.50
    POSITIVE LOGITS
    MENAFN
    0.92
    ContentAsync
    0.90
    IntoConstraints
    0.86
     مشين
    0.77
    enumi
    0.75
     kasarigan
    0.72
     DBNull
    0.72
    TagHelper
    0.70
    ThroughAttribute
    0.70
    ArrowToggle
    0.68
    Activations Density 0.086%

    No Known Activations