© 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. 10613
    Prev
    Next
    INDEX
    Explanations

    occurrences of the tab character or whitespace

    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
     yana
    -0.48
    дка
    -0.47
    记
    -0.44
    記
    -0.41
    良し
    -0.40
    ̣n
    -0.40
    ie
    -0.40
    ссе
    -0.40
    Se
    -0.40
     aina
    -0.40
    POSITIVE LOGITS
     للمعارف
    1.34
     للاسماء
    0.97
     tartalomajánló
    0.92
    tvguidetime
    0.91
     AssemblyCulture
    0.91
    StoryboardSegue
    0.90
    TagHelpers
    0.85
    UrlResolution
    0.84
     <<<<<<<<<<<<<<
    0.83
    Portail
    0.82
    Activations Density 0.037%

    No Known Activations