© 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. 19670
    Prev
    Next
    INDEX
    Explanations

    user interface components and programming terms

    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
     EClass
    -0.57
    EndInit
    -0.51
    addGap
    -0.49
    GraphicsUnit
    -0.47
    ɵɵ
    -0.47
    potranspiration
    -0.45
     SqlParameter
    -0.45
    THRESH
    -0.44
    lat
    -0.44
    itinéraire
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.75
     समीक्षाएं
    0.67
     ویکی‌پدی
    0.65
    fromnode
    0.65
     contextLoads
    0.64
     ErrIntOverflow
    0.63
    ChildScrollView
    0.62
     <<<<<<<<<<<<<<
    0.60
    település
    0.60
    ContentAsync
    0.57
    Activations Density 0.891%

    No Known Activations