© 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. 15918
    Prev
    Next
    INDEX
    Explanations

    positive affirmations or compositions related to superiority or quality

    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
    GetEnumerator
    -0.56
     fieldNum
    -0.53
    רושלים
    -0.50
    føring
    -0.49
     attitude
    -0.49
     boîtier
    -0.49
     let
    -0.46
    grafica
    -0.46
     pungkas
    -0.46
    Boas
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.67
     Italijanski
    0.67
    úrese
    0.66
    DEG
    0.59
    culable
    0.57
    期刊论文
    0.55
    EDEFAULT
    0.55
    googleapis
    0.54
     assister
    0.54
     سكانية
    0.54
    Activations Density 0.004%

    No Known Activations