© 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. 23341
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes and procedures involving usage, evaluation, and construction

    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
     imageNamed
    -0.58
     quang
    -0.55
     betweenstory
    -0.49
    MutableLiveData
    -0.47
    bootstrapcdn
    -0.46
    ęcz
    -0.43
     nhiêu
    -0.43
     disperse
    -0.42
    ########.
    -0.42
    float
    -0.42
    POSITIVE LOGITS
    
    0.82
    ⓧ
    0.80
    \}\\
    0.72
    addPreferredGap
    0.67
     autorytatywna
    0.66
    Tazama
    0.64
    twimg
    0.63
    CloseOperation
    0.63
    erialize
    0.62
     EnglishChoose
    0.62
    Activations Density 0.147%

    No Known Activations