© 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. 216
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments

    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
     Jefus
    -0.93
    DockStyle
    -0.91
     Monfieur
    -0.90
     purpoſe
    -0.89
     ſche
    -0.88
    Vidite
    -0.87
     itſelf
    -0.87
     myſelf
    -0.83
     Efq
    -0.82
     fubject
    -0.82
    POSITIVE LOGITS
    {
    0.58
    array
    0.52
    tabular
    0.51
    aligned
    0.49
     Soft
    0.46
    char
    0.44
     soft
    0.44
    迫
    0.44
    mtable
    0.43
    awt
    0.42
    Activations Density 0.115%

    No Known Activations