© 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. 24-RES-MATRYOSHKA-DC
    7. 1459
    Prev
    Next
    INDEX
    Explanations

    strings of special characters, likely used for formatting or denoting metadata

    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.24.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.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
     الرياضيه
    -0.71
     AssemblyCulture
    -0.67
     HasFactory
    -0.64
     الحره
    -0.64
    migrationBuilder
    -0.62
    ContextHolder
    -0.59
    tableFuture
    -0.59
     Ngb
    -0.59
     nakalista
    -0.58
     actionMode
    -0.58
    POSITIVE LOGITS
    
    0.92
     WR
    0.66
     W
    0.64
     DQ
    0.64
     RI
    0.63
     LQ
    0.63
     RQ
    0.60
    W
    0.59
     )
    0.59
     QR
    0.58
    Activations Density 0.013%

    No Known Activations