© 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. 8903
    Prev
    Next
    INDEX
    Explanations

    expressions related to the nature or characteristics of a situation, especially in legal or formal contexts

    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
    appartamento
    -0.62
     préf
    -0.60
     maksimal
    -0.57
     optimally
    -0.57
    cedures
    -0.56
    Activated
    -0.56
    ✨:
    -0.56
     bicolor
    -0.55
     Wirksamkeit
    -0.55
    perfectly
    -0.55
    POSITIVE LOGITS
    PyExc
    0.88
     nature
    0.69
    ImageContext
    0.68
     sifat
    0.67
     JAXBElement
    0.66
     dataType
    0.65
     TypeError
    0.63
    uberge
    0.63
     %>
    0.62
    LElement
    0.62
    Activations Density 0.009%

    No Known Activations