© 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. 20618
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "through" used in various contexts

    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
    qtype
    -0.68
    EndInit
    -0.62
    queryInterface
    -0.57
     all
    -0.54
     through
    -0.50
    addComponent
    -0.50
     que
    -0.49
     traverser
    -0.49
    ณ์
    -0.48
     into
    -0.48
    POSITIVE LOGITS
    berdayakan
    0.79
     كومونز
    0.76
     epig
    0.69
     seyn
    0.68
    tvguidetime
    0.68
     nicio
    0.65
     saveiro
    0.65
     vixion
    0.65
     élo
    0.64
    verwijspagina
    0.64
    Activations Density 0.019%

    No Known Activations