© 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. 25343
    Prev
    Next
    INDEX
    Explanations

    articles and determiners in the text

    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
     MonoBehaviour
    -0.49
    setopt
    -0.46
    mds
    -0.45
     poise
    -0.44
     Libri
    -0.44
    arity
    -0.44
     biografias
    -0.43
     لذلك
    -0.43
     Fern
    -0.43
     ditulis
    -0.42
    POSITIVE LOGITS
    GeneratedCode
    1.07
    省市镇
    1.05
    oredCriteria
    0.94
    Vidite
    0.93
     Савезне
    0.91
     externi
    0.91
     Italijanski
    0.88
    addCriterion
    0.87
     AssemblyCompany
    0.85
    WithIOException
    0.85
    Activations Density 0.364%

    No Known Activations