© 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. 30438
    Prev
    Next
    INDEX
    Explanations

    instances of the word "The" in various forms

    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
     transférez
    -0.54
    Music
    -0.50
     Music
    -0.47
    Des
    -0.47
    ولة
    -0.46
     Bons
    -0.43
     everyone
    -0.43
    Adapter
    -0.43
     fallu
    -0.42
    Mus
    -0.42
    POSITIVE LOGITS
     pinulongan
    0.86
     foncé
    0.76
    ScopeManager
    0.70
    AndEndTag
    0.64
     comuniques
    0.60
     rarement
    0.59
     بيها
    0.59
     (;;
    0.59
     defStyleAttr
    0.59
     altri
    0.58
    Activations Density 0.039%

    No Known Activations