© 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. 1087
    Prev
    Next
    INDEX
    Explanations

    text that describes things being listed in reverse chronological order or alphabetically, and also references to authors and books

    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
    ži
    -0.48
    migrationBuilder
    -0.45
    ∬
    -0.44
    ագրություններ
    -0.41
     attes
    -0.40
     Через
    -0.40
    范
    -0.39
    みの
    -0.39
    πε
    -0.39
     služ
    -0.38
    POSITIVE LOGITS
     chronological
    1.41
     order
    1.35
     alphabetical
    1.33
     ascending
    1.32
     alphabetically
    1.27
     sorted
    1.27
     ordered
    1.24
     Reihenfolge
    1.24
     descending
    1.23
     chronologically
    1.23
    Activations Density 1.224%

    No Known Activations