© 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. 21265
    Prev
    Next
    INDEX
    Explanations

    identifiers and unique ids associated with user or entity context

    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
     AssemblyCulture
    -0.93
    SuppressLint
    -0.85
     Elia
    -0.66
    +#+#
    -0.65
     Sampson
    -0.65
     FES
    -0.64
     Infórmanos
    -0.63
     endregion
    -0.63
     Acton
    -0.63
    djangoproject
    -0.63
    POSITIVE LOGITS
    uid
    1.25
     uid
    1.23
     UID
    1.08
    Uid
    0.93
    UID
    0.93
    getUid
    0.80
    uids
    0.80
     Cran
    0.79
     fVar
    0.72
    Демографія
    0.72
    Activations Density 0.001%

    No Known Activations