© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 25472
    Prev
    Next
    INDEX
    Explanations

    phrases with repetitive or redundant articles and prepositions

    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
    Negative Logits
    
    -0.70
    rungsseite
    -0.57
    verwijspagina
    -0.56
    awtextra
    -0.55
    Viitteet
    -0.52
    Спасылкі
    -0.52
    IVEREF
    -0.52
    Hozzáférés
    -0.50
     Corintios
    -0.48
     recevrez
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    1.03
    antMatchers
    0.75
    ]")]
    0.65
     nahilalakip
    0.63
    ancient
    0.62
     äldre
    0.60
     dAtA
    0.59
    sterious
    0.59
    ulent
    0.58
     untitled
    0.57
    Activations Density 0.145%

    No Known Activations