© 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. 336
    Prev
    Next
    INDEX
    Explanations

    rules and properties related to mathematical bounds, inequalities, and convergence criteria

    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
     Diſ
    -0.64
     Houſe
    -0.63
     houſe
    -0.60
     myſelf
    -0.60
     $_"
    -0.59
     Jefus
    -0.57
    bewerken
    -0.57
     Anſ
    -0.57
    tées
    -0.57
    ędziesz
    -0.55
    POSITIVE LOGITS
    n
    3.25
     n
    2.77
    ｎ
    1.69
    N
    1.62
    𝑛
    1.62
     N
    1.60
    𝗻
    1.43
    nn
    1.37
    nA
    1.34
    getN
    1.30
    Activations Density 0.593%

    No Known Activations