© 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. 15479
    Prev
    Next
    INDEX
    Explanations

    specific references to patent applications and their classification details

    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
     autorytatywna
    -0.85
    ElementException
    -0.85
    RepeatedField
    -0.81
    :"-"`
    -0.80
     StringTokenizer
    -0.79
    Personensuche
    -0.79
    AddTagHelper
    -0.77
    reactstrap
    -0.77
    üyada
    -0.75
    Билгалдахарш
    -0.75
    POSITIVE LOGITS
     WO
    0.91
    WO
    0.88
     global
    0.61
     Wo
    0.57
     PCT
    0.56
     Sen
    0.55
    Wo
    0.55
    global
    0.54
    wo
    0.54
     wo
    0.52
    Activations Density 0.014%

    No Known Activations