© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    sentence delimiters such as periods and commas, along with discourse markers such as "thus" or "especially"

    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
     nakalista
    -0.78
    protoc
    -0.75
    ^(@)
    -0.72
    OrBuilder
    -0.70
    multer
    -0.69
    }{*}{
    -0.69
    ])));
    -0.67
    他に
    -0.66
    )')
    -0.64
     Roskov
    -0.64
    POSITIVE LOGITS
     therefore
    2.38
     Therefore
    2.09
    Therefore
    2.08
     thus
    2.08
     hence
    2.06
    therefore
    1.95
     Hence
    1.87
    Consequently
    1.84
     Consequently
    1.83
    Hence
    1.82
    Activations Density 2.475%

    No Known Activations