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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 14060
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the duration of events or processes

    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
    AccessFile
    -0.90
     ControllerBase
    -0.77
    cetin
    -0.70
     Messi
    -0.69
     ModelExpression
    -0.69
    HttpPost
    -0.69
    chiato
    -0.69
    *}$
    -0.68
    )}>
    -0.68
    }">
    -0.68
    POSITIVE LOGITS
    DURATION
    0.96
    duration
    0.92
    Duration
    0.91
     Duration
    0.85
     DUR
    0.82
     duration
    0.81
     Durant
    0.77
     durations
    0.77
    Durant
    0.77
     Durand
    0.70
    Activations Density 0.008%

    No Known Activations