© 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. 20482
    Prev
    Next
    INDEX
    Explanations

    issues related to customer service experiences and product fulfillment problems

    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
    ftagPool
    -0.69
     мәкалә
    -0.63
     disambiguazione
    -0.63
    WriteAttribute
    -0.61
    MessageOf
    -0.58
    发表于
    -0.56
    NUMX
    -0.56
    matchCondition
    -0.55
    OOTDTY
    -0.55
    Auteur
    -0.53
    POSITIVE LOGITS
     customer
    0.63
     Customer
    0.56
     vuel
    0.56
     tjän
    0.53
    localctx
    0.52
     établissement
    0.52
     représ
    0.52
     compét
    0.52
     juridique
    0.52
     compétence
    0.52
    Activations Density 0.114%

    No Known Activations