© 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. 21752
    Prev
    Next
    INDEX
    Explanations

    phrases related to durations of time and periods of exposure

    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
    ViewImports
    -0.73
    VersionUID
    -0.69
    UnknownFields
    -0.64
     @"/
    -0.62
     péri
    -0.59
    chauss
    -0.56
     puberty
    -0.56
    icksburg
    -0.56
     htons
    -0.56
    /**
    -0.56
    POSITIVE LOGITS
     prolonged
    0.84
     duration
    0.71
    長時間
    0.65
     longer
    0.65
    stay
    0.65
    長く
    0.64
    duration
    0.63
    Duration
    0.62
    longer
    0.61
     length
    0.59
    Activations Density 0.161%

    No Known Activations