© 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. 1692
    Prev
    Next
    INDEX
    Explanations

    the beginning of the word "March" or "Marbury"

    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
     Vote
    -0.49
    webElementXpaths
    -0.49
     wire
    -0.48
    UnusedPrivate
    -0.48
    setBold
    -0.47
     teken
    -0.45
    🥞
    -0.45
    ckner
    -0.45
     afe
    -0.44
     itali
    -0.44
    POSITIVE LOGITS
     MAR
    0.72
     Mar
    0.68
     mar
    0.68
    mar
    0.67
    Mar
    0.66
     Margo
    0.62
     arşivlendi
    0.60
     Marg
    0.60
    MAR
    0.59
     Marlene
    0.58
    Activations Density 0.079%

    No Known Activations