© 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. 24030
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their usage in constructing sentences

    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
     EconPapers
    -0.94
    #
    -0.93
    ArgsConstructor
    -0.84
     autorytatywna
    -0.84
     nakalista
    -0.79
    enetrable
    -0.77
    ględ
    -0.77
     للمعارف
    -0.76
     Мексичка
    -0.76
    TagMode
    -0.75
    POSITIVE LOGITS
     sich
    0.83
     craindre
    0.69
     giảm
    0.67
     taget
    0.63
    कर
    0.63
    es
    0.62
    〉
    0.60
    면
    0.59
     however
    0.59
     prie
    0.59
    Activations Density 0.013%

    No Known Activations