© 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. 18845
    Prev
    Next
    INDEX
    Explanations

    references to study populations and their characteristics

    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
    InitVars
    -0.65
    contentLoaded
    -0.65
     dAtA
    -0.59
     Cæsar
    -0.59
    Билгалдахарш
    -0.59
    verwijspagina
    -0.59
     coö
    -0.58
    onViewCreated
    -0.58
    hots
    -0.58
    ValueStyle
    -0.57
    POSITIVE LOGITS
    Enfin
    0.51
    UIFont
    0.47
     context
    0.44
    واده
    0.43
     Enfin
    0.41
    ျ
    0.41
     الفلك
    0.41
     mati
    0.40
    Viel
    0.40
     berea
    0.40
    Activations Density 0.072%

    No Known Activations