© 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. 17038
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation in the text

    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
    WriteAttribute
    -0.55
    ябре
    -0.50
     "..\..\..\
    -0.49
     preprint
    -0.46
    цезда
    -0.46
    vince
    -0.46
     оригіналу
    -0.46
    PrototypeOf
    -0.46
    RefreshLayout
    -0.45
     raiſ
    -0.45
    POSITIVE LOGITS
    ="#"><
    0.59
    ".$_
    0.59
     }}"></
    0.56
    AccessException
    0.56
     BaseActivity
    0.56
    carril
    0.54
     hề
    0.54
    lüssel
    0.54
    ophanes
    0.54
    httphttps
    0.53
    Activations Density 0.004%

    No Known Activations