© 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. 9368
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs, particularly the word "to" with a following verb

    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
     ainfi
    -1.02
     poésie
    -0.96
     againſt
    -0.96
     pleaſure
    -0.93
     quæ
    -0.92
     poffible
    -0.91
     varandra
    -0.90
     becauſe
    -0.89
     umana
    -0.88
     charité
    -0.88
    POSITIVE LOGITS
    ’
    0.68
    (&_
    0.60
     appear
    0.58
     “
    0.56
    s
    0.55
     is
    0.54
     yang
    0.54
     ‘
    0.54
    .
    0.54
     (
    0.53
    Activations Density 0.086%

    No Known Activations