© 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. 2-RES-MATRYOSHKA-DC
    7. 4706
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or data

    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
    Véxase
    -0.72
    IntoConstraints
    -0.66
    ագրություններ
    -0.58
     Mardi
    -0.57
    хьтан
    -0.56
    bonucleic
    -0.55
    coming
    -0.54
    tvguidetime
    -0.54
    ikations
    -0.53
    ͘
    -0.53
    POSITIVE LOGITS
     numerical
    2.78
     Numerical
    2.53
    Numerical
    2.45
    numerical
    2.44
     numerically
    2.33
     numeric
    1.73
     Numer
    1.43
    数值
    1.41
     Numeric
    1.40
    numeric
    1.35
    Activations Density 0.019%

    No Known Activations