© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 22741
    Prev
    Next
    INDEX
    Explanations

    references to time-related phrases, particularly focusing on events that occur prior to a specified moment

    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
    DataInputStream
    -0.54
     first
    -0.53
     bien
    -0.53
    الدراسه
    -0.50
     union
    -0.48
     if
    -0.47
    疇
    -0.46
     before
    -0.46
     ou
    -0.46
    ุณ
    -0.44
    POSITIVE LOGITS
     Theſe
    0.87
    €)
    0.84
     myſelf
    0.77
     Jefus
    0.75
     becauſe
    0.74
     للاسماء
    0.74
    endphp
    0.73
    OrNil
    0.72
     Anſ
    0.71
    entibus
    0.71
    Activations Density 0.015%

    No Known Activations