© 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. 3-RES-MATRYOSHKA-DC
    7. 655
    Prev
    Next
    INDEX
    Explanations

    mathematical or physics notation, specifically the bra-ket notation

    oai_token-act-pair · gemini-2.0-flash
    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
     soeur
    -0.76
     datter
    -0.76
    Билгалдахарш
    -0.72
    InitStruct
    -0.71
     Xun
    -0.71
     crossorigin
    -0.68
    ături
    -0.66
     constater
    -0.65
    ändler
    -0.65
    ěst
    -0.63
    POSITIVE LOGITS
    langle
    2.78
    rangle
    1.91
    ⟨
    1.41
    〈
    1.30
     〈
    1.11
    〉
    1.00
    〈
    0.92
    ⟩
    0.88
    〉
    0.86
    lceil
    0.85
    Activations Density 0.050%

    No Known Activations