© 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. 28484
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure in programming-related text

    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
     disambiguazione
    -0.57
    曖昧さ回避
    -0.56
    yntaxException
    -0.55
     parroquia
    -0.54
     الرياضيه
    -0.52
    Рис
    -0.51
    findpost
    -0.51
    MPA
    -0.50
     estimés
    -0.50
    őbb
    -0.49
    POSITIVE LOGITS
     Alca
    0.71
    extAlignment
    0.69
     Schmitz
    0.65
     Caz
    0.64
    aarrggbb
    0.60
    PMailer
    0.60
     Skal
    0.59
    CANCE
    0.57
     Dok
    0.57
     Isolation
    0.57
    Activations Density 0.014%

    No Known Activations