© 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. 12127
    Prev
    Next
    INDEX
    Explanations

    concepts related to persistence and persistent states 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
    #+#
    -0.84
    gdx
    -0.81
    LLocation
    -0.80
    raulic
    -0.74
    anasia
    -0.74
    sidemargin
    -0.71
    __((
    -0.70
     Halen
    -0.69
     Havel
    -0.69
    ollectionView
    -0.67
    POSITIVE LOGITS
    persist
    1.01
     persist
    1.00
     Persistence
    0.91
    Persist
    0.91
     persistence
    0.90
    Persistence
    0.85
     persiste
    0.84
     persistent
    0.84
    persistent
    0.81
     Hoff
    0.79
    Activations Density 0.009%

    No Known Activations