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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11
    Prev
    Next
    INDEX
    Explanations

    programmatic structures and error handling related to Just-In-Time (JIT) compilation in code

    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
    TagMode
    -0.77
    <eos>
    -0.63
     
    -0.63
    __(/*!
    -0.60
    localctx
    -0.56
    HasColumnType
    -0.56
    RLock
    -0.54
     super
    -0.54
    EditorBrowsable
    -0.54
    IUrlHelper
    -0.52
    POSITIVE LOGITS
     houſe
    1.00
     pleaſure
    0.99
    neſs
    0.90
     purpoſe
    0.90
     Diſ
    0.88
     perſon
    0.88
     Reſ
    0.88
     Anſ
    0.86
     myſelf
    0.86
    ſelf
    0.86
    Activations Density 9.064%

    No Known Activations