© 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. 31996
    Prev
    Next
    INDEX
    Explanations

    phrases expressing equivalence or correspondence

    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
    rdı
    -0.80
     CreateTagHelper
    -0.77
    Composable
    -0.74
     <<<<<<<<<<<<<<
    -0.71
    Obrázky
    -0.69
    balleur
    -0.68
    addGroup
    -0.68
    Externí
    -0.67
     humains
    -0.67
     mellan
    -0.66
    POSITIVE LOGITS
     coincide
    1.13
     coincides
    1.04
     coinc
    1.01
     coincided
    0.81
     trùng
    0.79
     Palladium
    0.79
     officio
    0.77
     coincidence
    0.72
     coincident
    0.72
     Curs
    0.71
    Activations Density 0.005%

    No Known Activations