© 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. 21080
    Prev
    Next
    INDEX
    Explanations

    instances of specific geographical movements or travel activities

    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
    fetchall
    -0.51
    WriteBarrier
    -0.51
    ThemeOverlay
    -0.46
    ---*/
    -0.45
    AttributeSet
    -0.44
    breakpoints
    -0.43
    Brought
    -0.43
    textTheme
    -0.43
     ř
    -0.42
     Bru
    -0.41
    POSITIVE LOGITS
     Departure
    0.93
     departure
    0.88
    fromnode
    0.82
     partenza
    0.81
     depart
    0.80
    departure
    0.79
     départ
    0.79
    depart
    0.78
     departures
    0.78
    Depart
    0.77
    Activations Density 0.056%

    No Known Activations