© 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. 9569
    Prev
    Next
    INDEX
    Explanations

    terms related to virtual and augmented reality technologies

    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
    Datuak
    -0.67
    einander
    -0.61
     IPC
    -0.61
     RIV
    -0.61
    jasama
    -0.60
     Poitiers
    -0.60
     Ghosh
    -0.60
     Sparks
    -0.59
    częściej
    -0.59
     refriger
    -0.57
    POSITIVE LOGITS
     VR
    1.43
    VR
    1.21
     vr
    1.13
     Vr
    1.09
    Vr
    0.99
    vr
    0.95
     Oculus
    0.90
     headsets
    0.88
     Wra
    0.81
    jboss
    0.79
    Activations Density 0.007%

    No Known Activations