© 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. 5483
    Prev
    Next
    INDEX
    Explanations

    references to the concept of being flawless or ideal

    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
    olyb
    -0.66
     dignité
    -0.65
    ươi
    -0.65
    OfBirth
    -0.59
     relevant
    -0.59
    Relevant
    -0.59
     ارش
    -0.58
    \}\\
    -0.57
    relevant
    -0.57
     ilgili
    -0.57
    POSITIVE LOGITS
     perfect
    3.48
    perfect
    3.36
     Perfect
    3.16
    Perfect
    3.14
     PERFECT
    2.84
    PERFECT
    2.45
     perfecto
    2.42
     perfecta
    2.30
     perfecte
    2.25
     perfetto
    2.20
    Activations Density 0.010%

    No Known Activations