© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating necessity or obligation

    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
    Rujuakan
    -0.65
     onAnimation
    -0.65
    addCriterion
    -0.60
    jsxFileName
    -0.60
    XmlAccessType
    -0.55
    extends
    -0.53
    országban
    -0.52
    نگار
    -0.52
     scom
    -0.51
    ::_('
    -0.51
    POSITIVE LOGITS
     Must
    0.90
     must
    0.86
    Must
    0.83
    must
    0.80
    posterous
    0.77
     MUST
    0.76
    ."</
    0.68
    sure
    0.66
    Surely
    0.64
    LogService
    0.63
    Activations Density 0.052%

    No Known Activations