© 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. 25489
    Prev
    Next
    INDEX
    Explanations

    the word "to" 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
     auroit
    -0.99
     feroit
    -0.95
     témoins
    -0.91
     cérami
    -0.91
    tvguidetime
    -0.90
     élas
    -0.89
     lumineuse
    -0.88
     noemen
    -0.87
     boî
    -0.86
     LIRE
    -0.85
    POSITIVE LOGITS
    fsp
    0.70
     been
    0.61
    AsUp
    0.61
    logenetic
    0.60
     cel
    0.60
    ing
    0.57
    avadoc
    0.57
     asi
    0.56
    pperware
    0.56
    RESOLVED
    0.56
    Activations Density 0.022%

    No Known Activations