© 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. 20308
    Prev
    Next
    INDEX
    Explanations

    references to habits or habitual behavior

    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
    ="#"><
    -1.00
     scalars
    -0.90
     DCE
    -0.76
    )(((
    -0.74
     darbu
    -0.74
     Xeon
    -0.74
     posX
    -0.73
     Rinehart
    -0.73
     Doha
    -0.71
     Moura
    -0.71
    POSITIVE LOGITS
     Habit
    1.63
     Habits
    1.62
    Habit
    1.56
     habits
    1.51
     habit
    1.46
     HAB
    1.40
    habit
    1.34
    Hab
    1.25
     habitudes
    1.24
     Hab
    1.21
    Activations Density 0.006%

    No Known Activations