© 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. 21165
    Prev
    Next
    INDEX
    Explanations

    references to the user or interaction in a conversational 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
    
    -0.84
    Véxase
    -0.69
    Решение
    -0.65
     թվական
    -0.64
    حوالہ
    -0.62
    Vidite
    -0.61
    İstinadlar
    -0.60
    Aiheesta
    -0.57
    帖最后由
    -0.56
     Italijanski
    -0.55
    POSITIVE LOGITS
    تقاوى
    0.51
    SharedCtor
    0.50
     CreateTagHelper
    0.50
    ρχ
    0.48
    \
    0.48
    หนัง
    0.48
     interrog
    0.46
    сшта
    0.43
    CGRectMake
    0.43
    ValueGenerated
    0.42
    Activations Density 0.030%

    No Known Activations