© 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. 5974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating direction or destinations

    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
     into
    -0.56
    PreferredItem
    -0.54
    rachtet
    -0.51
     entrare
    -0.50
    queryInterface
    -0.47
     onto
    -0.47
    rungsseite
    -0.47
     saper
    -0.46
     tanong
    -0.46
     disambiguazione
    -0.46
    POSITIVE LOGITS
    Parcelize
    0.82
     destinations
    0.68
    EndGlobalSection
    0.68
     destination
    0.66
    bibitem
    0.65
    сылкі
    0.65
     CreateTagHelper
    0.63
    destination
    0.63
     назначения
    0.62
    enumi
    0.62
    Activations Density 0.175%

    No Known Activations