© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 961
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize inclusivity or totality

    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
    IUrlHelper
    -0.81
    出版年
    -0.80
    "}")
    -0.80
    )__
    -0.71
    jstor
    -0.71
     Napier
    -0.69
    yntaxException
    -0.68
    >--}}
    -0.67
    __':
    -0.67
    Viki
    -0.66
    POSITIVE LOGITS
     ALL
    1.41
     all
    1.32
    All
    1.28
    ALL
    1.22
     All
    1.21
    all
    1.16
     deleteAll
    1.11
    ReadAll
    1.08
     GetAll
    1.02
    llllllll
    0.95
    Activations Density 0.868%

    No Known Activations