© 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. 14927
    Prev
    Next
    INDEX
    Explanations

    phrases or references to specific individuals or groups with distinct 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
    җ
    -0.54
     مشين
    -0.52
    IsIn
    -0.50
     kos
    -0.49
    Comté
    -0.48
    تل
    -0.47
    LikeLike
    -0.46
     worin
    -0.46
    UIControlState
    -0.45
    wot
    -0.45
    POSITIVE LOGITS
    HostException
    0.73
     houſe
    0.72
     Majefty
    0.68
    ſelf
    0.68
     himſelf
    0.65
    RunAsync
    0.64
    niosek
    0.63
     Houſe
    0.61
     Efq
    0.60
     themſelves
    0.59
    Activations Density 0.044%

    No Known Activations