© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-RES-MATRYOSHKA-DC
    7. 1480
    Prev
    Next
    INDEX
    Explanations

    words that describe or suggest possible solutions or suggestions.

    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
    Negative Logits
    AndEndTag
    -0.92
    StoryboardSegue
    -0.88
    posedge
    -0.85
    MigrationBuilder
    -0.75
    InjectAttribute
    -0.73
     kasarigan
    -0.72
     successfully
    -0.70
    successfully
    -0.70
     Successfully
    -0.69
     quæ
    -0.69
    POSITIVE LOGITS
     simply
    1.08
     Instead
    1.04
     instead
    1.04
    Instead
    1.02
    干脆
    1.01
     use
    0.99
     Use
    0.94
    simply
    0.94
     opting
    0.92
     einfach
    0.91
    Activations Density 1.692%

    No Known Activations