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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-RES-MATRYOSHKA-DC
    7. 15119
    Prev
    Next
    INDEX
    Explanations

    that it makes tasks easier or simplifies the process

    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
     Stronger
    -0.69
     stronger
    -0.67
     darker
    -0.62
     happiest
    -0.60
     nearer
    -0.60
     fácilmente
    -0.59
     hotter
    -0.59
    RTLD
    -0.58
     darkest
    -0.57
     nonatomic
    -0.57
    POSITIVE LOGITS
     easier
    1.65
    easier
    1.44
     Easier
    1.27
    Easier
    0.98
     Normdatei
    0.73
    URLException
    0.73
     يتيمه
    0.70
    WebVitals
    0.69
     متعلقه
    0.65
    KommentareTeilen
    0.63
    Activations Density 0.003%

    No Known Activations