© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 10843
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons and measures related to clinical outcomes

    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
    یکن
    -0.49
     si
    -0.47
     kong
    -0.46
    úmenes
    -0.44
    pout
    -0.44
    FieldOffset
    -0.43
    sizePolicy
    -0.43
    Jereo
    -0.43
     mate
    -0.42
     impression
    -0.42
    POSITIVE LOGITS
     protoimpl
    0.79
     ExecuteAsync
    0.71
    Chham
    0.67
    AccessorTable
    0.67
     незавершена
    0.65
     saites
    0.64
    ViewFeatures
    0.59
    InputBorder
    0.59
    MigrationBuilder
    0.59
     <<<<<<<<<<<<<<
    0.57
    Activations Density 0.488%

    No Known Activations