© 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. 2419
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to time, especially focused on duration or deadlines.

    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
    principalTable
    -0.53
    γχ
    -0.50
    =}
    -0.47
    stums
    -0.47
    entikan
    -0.47
    spesies
    -0.46
    fjspx
    -0.45
     meneg
    -0.45
    ogs
    -0.44
     renou
    -0.44
    POSITIVE LOGITS
     preparation
    3.25
     Preparation
    2.92
     prepare
    2.88
     prepared
    2.83
    preparation
    2.81
     preparations
    2.80
     preparing
    2.75
     prepares
    2.70
    Preparation
    2.69
     PREPARATION
    2.63
    Activations Density 0.956%

    No Known Activations