© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 16373
    Prev
    Next
    INDEX
    Explanations

    semicolons and function call terminators

    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
    Personendaten
    -1.11
    +#+
    -1.05
    Parcelize
    -1.00
    GEBURTSDATUM
    -0.98
    ImageContext
    -0.96
     kasarigan
    -0.94
     &___
    -0.94
    endphp
    -0.91
     nakalista
    -0.90
     دیکھیے
    -0.89
    POSITIVE LOGITS
    netty
    0.55
    ty
    0.44
    af
    0.44
     Thi
    0.44
    ufel
    0.44
     recol
    0.44
    makeConstraints
    0.43
    ark
    0.41
     let
    0.39
    ห์
    0.39
    Activations Density 0.006%

    No Known Activations