© 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. 1630
    Prev
    Next
    INDEX
    Explanations

    hexadecimal code

    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
     Willoughby
    -0.52
    granate
    -0.52
     Stanisław
    -0.48
    cillor
    -0.47
     الحره
    -0.46
    emplare
    -0.46
    butyl
    -0.44
     abbandon
    -0.44
     établissements
    -0.44
     Beverly
    -0.44
    POSITIVE LOGITS
    9
    1.04
     Nine
    1.03
     nine
    1.02
     Ninth
    0.94
    Nine
    0.94
     ninth
    0.93
    九
    0.91
     NINE
    0.91
     nueve
    0.86
     九
    0.83
    Activations Density 1.388%

    No Known Activations