© 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. 9820
    Prev
    Next
    INDEX
    Explanations

    past tense verbs that indicate actions or events related to time and sequence

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ollectionView
    -0.68
     récomp
    -0.65
     présidenti
    -0.65
     traités
    -0.64
     marié
    -0.63
    colnshire
    -0.63
    ardless
    -0.62
    phazard
    -0.61
     témoin
    -0.61
    PreferredItem
    -0.60
    POSITIVE LOGITS
     earlier
    1.02
    earlier
    0.84
     Earlier
    0.82
    Earlier
    0.79
     hadn
    0.76
     disambiguazione
    0.74
     previously
    0.70
     hoped
    0.69
     previous
    0.69
     дописавши
    0.66
    Activations Density 0.183%

    No Known Activations