© 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. 6368
    Prev
    Next
    INDEX
    Explanations

    references to coding or programming constructs, particularly focusing on object-oriented programming practices and structures

    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
    EndGlobalSection
    -0.86
    enumii
    -0.83
    WithIOException
    -0.82
    awtextra
    -0.76
    IsContent
    -0.74
    ValueStyle
    -0.74
    AddTagHelper
    -0.73
    IntoConstraints
    -0.73
    cshtml
    -0.69
    IsMutable
    -0.69
    POSITIVE LOGITS
    aliyun
    0.60
    xically
    0.53
    rigkeit
    0.52
     depan
    0.49
    Dichloropropene
    0.47
    族館
    0.46
     cellspacing
    0.45
     software
    0.45
     MacLeod
    0.45
    teen
    0.44
    Activations Density 0.643%

    No Known Activations