Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 26736
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific procedural or legal requirements

    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
     or
    -0.50
     either
    -0.48
    alip
    -0.47
    DotNetBar
    -0.47
     protoimpl
    -0.46
    xaml
    -0.44
    WindowEvent
    -0.44
    odis
    -0.43
    urlencoded
    -0.43
    渉
    -0.42
    POSITIVE LOGITS
     betweenstory
    0.80
    MigrationBuilder
    0.73
     ainfi
    0.64
     Wikimedijinoj
    0.60
     auffi
    0.59
    expandindo
    0.59
     elsewhere
    0.58
     abstrait
    0.58
     himſelf
    0.57
     HasFactory
    0.57
    Activations Density 0.401%

    No Known Activations