© 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. 22-RES-MATRYOSHKA-DC
    7. 1826
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming language-related terms

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    peq
    -0.59
    WaitGroup
    -0.59
     invokingState
    -0.58
    CloseOperation
    -0.54
     Affiliations
    -0.49
    CardBody
    -0.47
    AsUp
    -0.47
    npmjs
    -0.47
    MeasureSpec
    -0.47
     onAnimation
    -0.47
    POSITIVE LOGITS
     translation
    1.28
     translations
    1.27
     translators
    1.25
     translated
    1.18
     translator
    1.16
     Translation
    1.16
     translate
    1.15
     translating
    1.10
    translation
    1.09
     Translations
    1.09
    Activations Density 0.797%

    No Known Activations