© 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. 796
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    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
     feroit
    -0.92
     avoient
    -0.91
     auroit
    -0.90
     étoit
    -0.85
    rsiniz
    -0.84
    PositiveButton
    -0.78
     acrylique
    -0.77
    WebMethod
    -0.77
     étoient
    -0.77
     ainfi
    -0.73
    POSITIVE LOGITS
     purpose
    0.54
     
    0.51
     K
    0.49
     He
    0.49
     set
    0.48
     \
    0.48
    aya
    0.47
    蔔
    0.46
     publi
    0.46
    .
    0.45
    Activations Density 0.011%

    No Known Activations