© 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. 690
    Prev
    Next
    INDEX
    Explanations

    patterns related to mathematical norms and inequalities

    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
    |
    -0.86
     Cæsar
    -0.67
     lèvres
    -0.65
    cyj
    -0.64
     dommages
    -0.63
    ltä
    -0.60
     encendido
    -0.60
     incendie
    -0.60
     recrutement
    -0.59
     saveur
    -0.59
    POSITIVE LOGITS
    \|
    3.44
    \|\
    2.61
     \|
    2.33
    }\|
    2.08
     $\|
    1.96
    \|^{
    1.84
    \|_{
    1.51
    ∥
    1.44
    \|_{\
    1.33
    ‖
    1.11
    Activations Density 0.098%

    No Known Activations