© 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. 21677
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time

    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
     pronti
    -0.56
     Browne
    -0.50
    thra
    -0.50
    INSERT
    -0.49
    cki
    -0.49
     Schulte
    -0.48
     hal
    -0.48
     Aguirre
    -0.48
    正
    -0.48
     ready
    -0.48
    POSITIVE LOGITS
    клопе
    0.94
     itſelf
    0.81
    .';
    0.78
     myſelf
    0.78
     CreateTagHelper
    0.77
    曖昧さ回避
    0.75
     ujednoznacz
    0.72
     iſt
    0.71
    ]))
    0.71
    🏻‍♀️
    0.71
    Activations Density 0.028%

    No Known Activations