© 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. 26262
    Prev
    Next
    INDEX
    Explanations

    terms referring to people or items in a casual or informal 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
     Rebekah
    -0.79
    y
    -0.79
     Maro
    -0.75
     Norma
    -0.73
     Holman
    -0.72
     Aper
    -0.69
    nder
    -0.68
     Bianca
    -0.68
    mah
    -0.68
    aper
    -0.68
    POSITIVE LOGITS
     GUYS
    1.18
     Stuff
    1.12
     GUY
    1.11
    guys
    1.09
     Guy
    1.08
     stuff
    1.06
    Guys
    1.06
    Stuff
    1.04
     Guys
    1.02
    guy
    1.01
    Activations Density 0.022%

    No Known Activations