© 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. 12-RES-MATRYOSHKA-DC
    7. 26728
    Prev
    Next
    INDEX
    Explanations

    sequences of escape characters in code snippets

    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
     lang
    -0.66
     estimés
    -0.64
     est
    -0.62
     lo
    -0.60
    ATR
    -0.58
     am
    -0.57
     Ach
    -0.56
    ebles
    -0.56
     Lang
    -0.54
     den
    -0.54
    POSITIVE LOGITS
     Efq
    1.05
     itſelf
    1.05
     himſelf
    1.02
     myſelf
    1.02
     purpoſe
    1.01
     Theſe
    0.99
     Monfieur
    0.97
     reaſon
    0.95
     ejus
    0.93
     themſelves
    0.91
    Activations Density 0.027%

    No Known Activations