© 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. 9933
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preferences or choices

    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
    EndContext
    -0.44
     gew
    -0.44
    AddTagHelper
    -0.43
     deta
    -0.43
    Kle
    -0.43
    A
    -0.42
    ffffffff
    -0.40
     Kard
    -0.40
    Dichloropropane
    -0.40
    copyWith
    -0.40
    POSITIVE LOGITS
    出版年
    0.71
    ostante
    0.65
    NOPQRST
    0.65
     espont
    0.62
    gelopen
    0.61
    Parcelize
    0.60
    wikidata
    0.60
    oused
    0.59
    ioutil
    0.58
    bbene
    0.57
    Activations Density 0.299%

    No Known Activations