© 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. 22-RES-MATRYOSHKA-DC
    7. 2964
    Prev
    Next
    INDEX
    Explanations

    a mishmash of mostly unrelated things, including wicca, science article identifiers, and the suffix "ist"

    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.22.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.22.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
    Datuak
    -1.05
     ostavi
    -0.98
    клопе
    -0.92
     Italijanski
    -0.92
    ✨:
    -0.88
     iſt
    -0.85
     $_(
    -0.85
    SharedDtor
    -0.84
    djangoproject
    -0.84
    bootstrapcdn
    -0.84
    POSITIVE LOGITS
     j
    0.42
     
    0.42
     i
    0.39
     pro
    0.37
     at
    0.36
     a
    0.36
     tech
    0.36
     bu
    0.35
     roz
    0.35
     pl
    0.34
    Activations Density 0.011%

    No Known Activations