© 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. 28516
    Prev
    Next
    INDEX
    Explanations

    terms related to cases or instances being discussed or analyzed

    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
     myſelf
    -0.62
    readFileSync
    -0.62
    AnchorStyles
    -0.60
     faſt
    -0.60
     Мексичка
    -0.59
     Pixabay
    -0.59
     pixabay
    -0.59
     YAML
    -0.57
     htons
    -0.56
     edn
    -0.56
    POSITIVE LOGITS
     Inoue
    0.60
     original
    0.55
    GIVEREF
    0.55
     juos
    0.53
    inder
    0.52
     Crowe
    0.52
    oyan
    0.52
    værk
    0.52
    contentPane
    0.52
    robial
    0.51
    Activations Density 0.029%

    No Known Activations