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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11075
    Prev
    Next
    INDEX
    Explanations

    references to location and setting in a narrative context

    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
     wireType
    -0.75
    Erstellt
    -0.71
     createSprite
    -0.61
    IntoConstraints
    -0.58
    errHandler
    -0.58
     suffrage
    -0.57
     ordination
    -0.57
     attentes
    -0.56
     hentai
    -0.55
     rospy
    -0.54
    POSITIVE LOGITS
    Referenced
    0.65
     autorytatywna
    0.58
     references
    0.54
    references
    0.54
     confund
    0.52
    AsUp
    0.52
     Insee
    0.52
     appear
    0.52
    WireFormatLite
    0.51
     Misch
    0.49
    Activations Density 0.041%

    No Known Activations