© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    repetitive uses of the word "numerous."

    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
    UIControlState
    -0.86
    Smarty
    -0.81
    Zaj
    -0.75
     HasFactory
    -0.74
    moiselle
    -0.72
     Gerv
    -0.70
     Balth
    -0.69
    5
    -0.68
     Mademoiselle
    -0.67
    🔽
    -0.66
    POSITIVE LOGITS
     للمعارف
    0.83
    logenetic
    0.72
    maxcdn
    0.71
    rigues
    0.69
     серпня
    0.67
    [--
    0.67
    numer
    0.66
     Kosten
    0.66
     مرئيه
    0.66
     eventuali
    0.66
    Activations Density 0.007%

    No Known Activations