© 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. 13297
    Prev
    Next
    INDEX
    Explanations

    estimates related to statistical parameter assessments and model fit, particularly focusing on estimates of uncertainty, regression, and population variation

    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
     Мексичка
    -0.88
     Estimation
    -0.85
     estimation
    -0.82
    AutoScaleMode
    -0.82
     approximated
    -0.82
     يتيمه
    -0.81
     approx
    -0.79
     насељу
    -0.77
    approximately
    -0.76
     approximate
    -0.75
    POSITIVE LOGITS
     estimates
    1.53
     Estimates
    1.40
    Estimates
    1.09
    estimates
    0.91
     advocates
    0.59
     simply
    0.49
    chufe
    0.47
     дори
    0.46
     Prä
    0.45
    kelen
    0.45
    Activations Density 0.003%

    No Known Activations