© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16448
    Prev
    Next
    INDEX
    Explanations

    action verbs related to fleeing or escaping

    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
    Not in Any Lists

    No Comments

    Negative Logits
    StoreMessageInfo
    -0.80
    inerario
    -0.69
    viewType
    -0.69
     Voyages
    -0.69
     Sins
    -0.67
    Ligações
    -0.66
     autorytatywna
    -0.66
     Gough
    -0.66
     travelling
    -0.66
    trav
    -0.65
    POSITIVE LOGITS
     Run
    0.67
     Sprint
    0.62
     sprint
    0.61
     ran
    0.57
    Run
    0.56
     spr
    0.56
     falt
    0.55
     sprinter
    0.54
     running
    0.54
    PerformLayout
    0.53
    Activations Density 0.022%

    No Known Activations