© 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. 22-RES-MATRYOSHKA-DC
    7. 2062
    Prev
    Next
    INDEX
    Explanations

    times of day

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    HtmlAttribute
    -0.79
     <=",
    -0.74
     gyhoeddwyd
    -0.72
    ⓘ
    -0.70
    parsedMessage
    -0.65
     ་་
    -0.65
     {})
    -0.64
    [++
    -0.64
    IUrlHelper
    -0.63
    enterOuterAlt
    -0.63
    POSITIVE LOGITS
     Eastern
    0.82
     EST
    0.81
     ET
    0.76
     local
    0.75
     Central
    0.73
     PST
    0.72
     EDT
    0.71
    Eastern
    0.68
     central
    0.66
     eastern
    0.66
    Activations Density 0.067%

    No Known Activations