© 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. 18-RES-MATRYOSHKA-DC
    7. 543
    Prev
    Next
    INDEX
    Explanations

    the letters "E" and "g" and sometimes terms related to ebooks or insects

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     >=",
    -0.77
    fjspx
    -0.72
     <=",
    -0.70
     архивлан
    -0.68
    WindowConstants
    -0.68
     Wicidata
    -0.67
    SharedDtor
    -0.65
     updatedAt
    -0.63
    جراء
    -0.63
    SPJ
    -0.63
    POSITIVE LOGITS
     Eel
    0.64
     Estrada
    0.64
     EG
    0.60
     Eles
    0.59
     EA
    0.59
     E
    0.59
     Esk
    0.57
     Eier
    0.57
     ESTR
    0.56
     éc
    0.56
    Activations Density 2.108%

    No Known Activations