© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 13684
    Prev
    Next
    INDEX
    Explanations

    the presence of dielectric materials and related phenomena in scientific and technical texts

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NET
    -1.16
    net
    -0.89
    nets
    -0.73
    aarrggbb
    -0.67
    nete
    -0.58
    רת
    -0.53
    Net
    -0.52
    )");
    -0.52
    ！");
    -0.52
    ']?>
    -0.52
    POSITIVE LOGITS
     net
    1.91
    AutoScaleMode
    0.96
     nets
    0.79
     autorytatywna
    0.77
     Italijanski
    0.73
     netting
    0.71
     netted
    0.70
     ordf
    0.66
     maternidade
    0.64
     devriez
    0.63
    Activations Density 0.007%

    No Known Activations