© 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. 8834
    Prev
    Next
    INDEX
    Explanations

    references to timing and the significance of timing in various contexts

    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
    parsedMessage
    -0.84
    RegressionTest
    -0.77
    setVerticalGroup
    -0.71
    ecore
    -0.69
    ThroughAttribute
    -0.69
     resourceCulture
    -0.69
    bitField
    -0.68
    SourceChecksum
    -0.65
    o
    -0.63
     Zain
    -0.63
    POSITIVE LOGITS
    timing
    1.23
     Timing
    1.23
    Timing
    1.20
     timing
    1.13
    timed
    0.84
     tombé
    0.84
     timed
    0.83
     timings
    0.80
    onoi
    0.77
     germination
    0.77
    Activations Density 0.006%

    No Known Activations