© 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. 414
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like "const", "function", and "expression"

    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
     Quig
    -0.49
     qued
    -0.48
    TypedDataSet
    -0.47
     configured
    -0.47
    configured
    -0.46
     gomma
    -0.46
     feltro
    -0.46
    ջ
    -0.45
    discre
    -0.45
    amani
    -0.44
    POSITIVE LOGITS
    ftagPool
    0.82
     للمعارف
    0.77
     compiler
    0.70
    plevel
    0.68
    省市镇
    0.66
     declara
    0.66
     expression
    0.66
    хьтан
    0.64
     declarations
    0.63
     declaration
    0.62
    Activations Density 3.095%

    No Known Activations