© 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. 658
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing relationships or connections between different entities or concepts

    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
     spese
    -0.66
    viewDidLoad
    -0.63
     scalars
    -0.56
     Prussia
    -0.55
     piú
    -0.54
     histamine
    -0.54
     comigo
    -0.54
    ophone
    -0.54
     cérami
    -0.54
    Dope
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.73
    migrationBuilder
    0.71
     للمعارف
    0.67
    erdings
    0.66
    setminus
    0.66
    glMatrixMode
    0.66
     the
    0.65
     समीक्षाएं
    0.64
     also
    0.63
     المعيارى
    0.63
    Activations Density 0.836%

    No Known Activations