© 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. 30153
    Prev
    Next
    INDEX
    Explanations

    references to literals in programming or markup languages

    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
    #+#
    -1.21
    ChildScrollView
    -1.12
     Савезне
    -1.05
     الرياضيه
    -0.99
    adaptiveStyles
    -0.99
    AddTagHelper
    -0.98
    IUrlHelper
    -0.98
     EconPapers
    -0.94
     CreateTagHelper
    -0.94
     متعلقه
    -0.92
    POSITIVE LOGITS
     
    0.50
     numériques
    0.45
     herein
    0.42
    duga
    0.40
     ho
    0.39
     literals
    0.39
    literal
    0.39
     $
    0.39
     Ho
    0.38
     candidat
    0.38
    Activations Density 0.010%

    No Known Activations