© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-RES-MATRYOSHKA-DC
    7. 789
    Prev
    Next
    INDEX
    Explanations

    phrases containing unbounded values or approaching infinity

    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
    DOM
    -0.55
     переписи
    -0.55
    Goods
    -0.52
     Goods
    -0.51
    Divider
    -0.51
    出版年
    -0.51
    زم
    -0.50
     Rober
    -0.49
    dis
    -0.49
     miesz
    -0.49
    POSITIVE LOGITS
    infty
    4.91
    ∞
    3.41
     ∞
    2.92
    infinity
    2.42
     infinity
    2.31
    Infinity
    1.92
     Infinity
    1.90
    
    1.72
     infinite
    1.66
    Infinite
    1.61
    Activations Density 0.049%

    No Known Activations