© 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. 12-RES-MATRYOSHKA-DC
    7. 9570
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation marks

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.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.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Negative Logits
    ſelves
    -1.05
    BibitemShut
    -1.00
     iſt
    -0.97
     Anſ
    -0.97
     Efq
    -0.93
    ſelf
    -0.90
     Majefty
    -0.90
     XNUMX
    -0.90
     raiſ
    -0.88
     Arhivirano
    -0.84
    POSITIVE LOGITS
    ;
    0.68
    t
    0.63
    [toxicity=0]
    0.61
    racene
    0.59
    !
    0.58
    ٰ
    0.57
    s
    0.55
    ://
    0.54
    €“
    0.54
    \|
    0.52
    Activations Density 0.019%

    No Known Activations