© 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
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 10907
    Prev
    Next
    INDEX
    Explanations

    legal citations and references to statutory codes

    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
     fej
    -0.48
    oplastic
    -0.48
    enez
    -0.47
     stanu
    -0.47
    ώρα
    -0.46
    мора
    -0.45
    met
    -0.45
    дж
    -0.45
    tej
    -0.45
    getSub
    -0.45
    POSITIVE LOGITS
    DockStyle
    1.03
     EconPapers
    0.89
    IndentedString
    0.83
    AnchorStyles
    0.81
    ChildScrollView
    0.77
     NSCoder
    0.77
    ParallelGroup
    0.73
     InputDecoration
    0.73
     متعلقه
    0.72
     AssemblyCulture
    0.71
    Activations Density 0.016%

    No Known Activations