© 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. 9941
    Prev
    Next
    INDEX
    Explanations

    terms related to dispersion and distribution

    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
    ggiamento
    -0.70
     оригіналу
    -0.68
    ので
    -0.66
    gatt
    -0.65
    dtd
    -0.65
    ersburg
    -0.63
    giène
    -0.63
    itados
    -0.62
    titleLabel
    -0.62
    łk
    -0.60
    POSITIVE LOGITS
     Dispersion
    1.46
     dispersion
    1.38
    persion
    1.32
     disper
    1.01
    клопе
    0.99
     JSTOR
    0.97
    httphttps
    0.93
     depositphotos
    0.88
    persed
    0.87
     disperse
    0.85
    Activations Density 0.004%

    No Known Activations