© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11927
    Prev
    Next
    INDEX
    Explanations

    terms related to botany and natural sciences, particularly those involving herbs and plant taxonomy

    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
     Lightboxes
    -0.99
     InputDecoration
    -0.87
    Diwedd
    -0.86
     Titi
    -0.84
     NSCoder
    -0.83
    $")
    -0.82
    abestanden
    -0.80
     Quicks
    -0.79
    ViewFeatures
    -0.79
    mybatisplus
    -0.79
    POSITIVE LOGITS
     Erm
    0.86
     Herzog
    0.86
     Gers
    0.82
     Hermans
    0.82
    erp
    0.79
     herbs
    0.78
     Er
    0.77
    vertx
    0.76
     Hertz
    0.73
     ERP
    0.71
    Activations Density 0.228%

    No Known Activations