© 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. 19992
    Prev
    Next
    INDEX
    Explanations

    syntactical variations and patterns in structured data or code snippets

    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
    pexpr
    -0.52
    مصادر
    -0.50
     نش
    -0.48
    intrag
    -0.45
    apj
    -0.43
     Abp
    -0.43
     bouch
    -0.43
    Referencies
    -0.43
    psin
    -0.42
     webbplats
    -0.41
    POSITIVE LOGITS
     propOrder
    1.05
    VersionUID
    0.70
    ﹍﹍﹍
    0.65
     "..\..\..\
    0.61
     BoxFit
    0.61
     ffilm
    0.60
     betweenstory
    0.60
     CanadaChoose
    0.59
    tagext
    0.58
    何より
    0.56
    Activations Density 0.080%

    No Known Activations