© 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. 13800
    Prev
    Next
    INDEX
    Explanations

    references to artificial intelligence and related concepts

    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
     Descriptor
    -0.81
     Ryder
    -0.79
    ükü
    -0.71
    descriptor
    -0.70
     المش
    -0.69
     Poste
    -0.69
     Jakob
    -0.68
    нивер
    -0.68
     Krug
    -0.68
    ="{{$
    -0.67
    POSITIVE LOGITS
     AI
    1.27
    AI
    1.09
     Artificial
    1.09
     Ai
    1.07
     ai
    1.03
    Ai
    1.02
    Artificial
    1.02
    artificial
    0.95
     artificial
    0.93
     artificiales
    0.91
    Activations Density 0.009%

    No Known Activations