© 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. 384
    Prev
    Next
    INDEX
    Explanations

    scientific or medical texts related to studies and models

    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
     voyez
    -0.66
    Tikang
    -0.64
     Obviously
    -0.61
     oftentimes
    -0.61
     đôi
    -0.59
     Lately
    -0.59
    Figura
    -0.58
    anmoins
    -0.58
     Similarly
    -0.58
    Sadly
    -0.58
    POSITIVE LOGITS
    ."</
    0.65
    documentclass
    0.55
    ]]=
    0.54
    ."<
    0.53
    MigrationBuilder
    0.53
    .")]
    0.51
     eighteen
    0.51
     ..."
    0.50
    .""
    0.49
    "--
    0.48
    Activations Density 2.522%

    No Known Activations