© 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. 30710
    Prev
    Next
    INDEX
    Explanations

    terminology related to tightness or constriction in various contexts

    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
     esser
    -0.73
    wpdb
    -0.71
    Pel
    -0.65
     pel
    -0.64
     Holbrook
    -0.64
     Marcell
    -0.63
    TabIndex
    -0.63
    Dakota
    -0.63
     Cardano
    -0.62
    Ger
    -0.61
    POSITIVE LOGITS
    Tight
    1.70
     tight
    1.66
     Tight
    1.66
    tight
    1.58
     tightness
    1.41
     tightly
    1.39
     tighter
    1.34
     tighten
    1.24
     tightened
    1.20
     tightening
    1.12
    Activations Density 0.010%

    No Known Activations